Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
DETAILED ACTION
This is a reply to the application filed on 11/04/2024, in which, claims 1-20 are pending. Claims 1, 11, and 20 are independent.
When making claim amendments, the applicant is encouraged to consider the references in their entireties, including those portions that have not been cited by the examiner and their equivalents as they may most broadly and appropriately apply to any particular anticipated claim amendments.
Drawings
The drawings filed on 11/04/2024 are accepted
Specification
The disclosure filed on 11/04/2024 is accepted
Information Disclosure Statement
The information disclosure statements (IDS) submitted on 02/27/2025 is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Claim Interpretation
The following is a quotation of 35 U.S.C. 112(f):
(f) Element in Claim for a Combination. – An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
The following is a quotation of pre-AIA 35 U.S.C. 112, sixth paragraph:
An element in a claim for a combination may be expressed as a means or step for performing a specified function without the recital of structure, material, or acts in support thereof, and such claim shall be construed to cover the corresponding structure, material, or acts described in the specification and equivalents thereof.
This application includes one or more claim limitations that do not use the word "means," but are nonetheless being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, because the claim limitation(s) uses a generic placeholder that is coupled with functional language without reciting sufficient structure to perform the recited function and the generic placeholder is not preceded by a structural modifier. Such claim limitation(s) is/are: "a voice clone detection bot" in claim 1.
Because this claim limitation is being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, it is being interpreted to cover the corresponding structure described in the specification as performing the claimed function, and equivalents thereof. The specification describes the voice clone detection bot 12 as software running on a user's computing device, such as an endpoint device, that inserts itself into phone applications, online meeting applications, or other voice-driven applications and integrates with a client sensor agent (paragraph [0024]: "The voice clone detection bot 12 inserts itself into one or more of a phone application, an online meeting application, or other voice driven application resident on the computing device of the user and then monitors that application."). The specification further describes the bot as using a VAD (Voice Activity Detector) to detect speech, splitting audio into 8-15 second chunks, and forwarding real-time audio segments to the cloud service platform via a secure connection (paragraph [0024]: "The voice clone detection bot 12 can use a VAD (Voice Activity Detector) to determine where speech is in the audio file and trim silences between. The voice clone detection bot 12 deduces where sentences end in the audio file under analysis with an array and splits the audio file into chunks (at sentence ends where possible) of 8-15 seconds.").
If applicant does not intend to have this limitation interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph, applicant may: (1) amend the claim limitation to avoid it being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph (e.g., by reciting sufficient structure to perform the claimed function); or (2) present a sufficient showing that the claim limitation recites sufficient structure to perform the claimed function so as to avoid it being interpreted under 35 U.S.C. 112(f) or pre-AIA 35 U.S.C. 112, sixth paragraph.
Claim Rejections - 35 USC § 101
35 U.S.C. 101 reads as follows:
Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title.
Claims 1-10 are rejected under 35 U.S.C. 101 because the claimed invention is not directed to patent eligible subject matter.
Claim 1 is not directed to any statutory category of invention.
Under Step 1 of the eligibility analysis (MPEP 2106.03), a claim must fall within at least one of the four statutory categories: process, machine, manufacture, or composition of matter. A claim whose broadest reasonable interpretation includes non-statutory embodiments embraces subject matter that is not eligible for patent protection and fails Step 1. Non-limiting examples of claims that fall outside the statutory categories include products that do not have a physical or tangible form, such as a computer program per se ("software per se").
The following limitations, under their broadest reasonable interpretation, are software per se and do not fall within any statutory category:
A cyber security system to protect against cyber threats including a synthetic clone of a voice of a speaker (software per se; the claimed "system" does not positively recite any hardware, processor, memory, or tangible structure.)
a deep learning model trained to analyze an audio file input into the deep learning model and to produce as an output one or more embeddings of the audio file, under analysis (software per se; a deep learning model does not inherently require or recite any particular hardware.)
one or more AI classifiers trained to analyze the one or more embeddings of the audio file, under analysis, from the deep learning model to determine whether it is likely that the voice of the speaker engaging with a user is real or the synthetic clone of the voice of the speaker (software per se; AI classifiers are software algorithms or mathematical models that process inputs and produce classification outputs, without inherently requiring hardware.)
a voice clone detection bot configured to be resident on a computing device of the user and to integrate with different sources of audio data on the computing device of the user in order to collect the audio file containing an attempt to synthetically clone the voice of the speaker protected by the cyber security system (software per se; "voice clone detection bot" is a nonce term that invokes 35 U.S.C. 112(f). If the corresponding structure disclosed in the specification is only software per se or not disclosed (not tied to a specific algorithm implemented on a computer or microprocessor) the limitation lacks sufficient structure. Here, the specification does not disclose a specific algorithm implemented on a specific machine for the "voice clone detection bot." The bot is described only functionally as software.)
Although the limitation recites that the bot is "configured to be resident on a computing device of the user," this language describes where the software resides, not what the system structurally comprises. The "computing device of the user" is recited as a location for the bot, not as a positively recited structural component of the claimed "cyber security system."
Dependent 1-3 claims do not cure the deficiency of the independent claims and are therefore rejected based on the aforementioned rationale.
Dependent claims 5, 7, and 9-10 pertain to adding a binary AI classifier to evaluate combined determinations of likelihood; adding a deepfake detector module that sends a message to the user or shuts down an application upon detection; performing audio preprocessing such as splitting audio into individual sentences and organizing audio chunks by speaker; allowing a user to manually upload an audio file via a user interface; and generating synthetic voice data for training, all without positively reciting any hardware as a structural component of the claimed system, and therefore without bringing the claims within any statutory category.
Claims 4 merely recite receiving likelihood determinations from other classifiers and evaluating them to make a real-or-fake determination, which are further software operations, without positively reciting any hardware or bringing the claims within any statutory category.
Claim Rejections - 35 USC § 112
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
The following is a quotation of the first paragraph of pre-AIA 35 U.S.C. 112:
The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor of carrying out his invention.
Claims 1-20 is rejected under 35 U.S.C. 112(a) as failing to comply with the written description requirement. The claim contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor had possession of the claimed invention.
Claims 1, 11 and 20 recites the 112(f) limitation "a voice clone detection bot." The specification does not provide a disclosure of the computer and algorithm in sufficient detail to demonstrate to one of ordinary skill in the art that the inventor possessed the invention. The specification describes the voice clone detection bot 12 only in terms of its functions without disclosing an algorithm or procedure for how the bot accomplishes these functions. For software, the algorithm or steps/procedure taken to perform the function must be described with sufficient detail so that one of ordinary skill in the art would understand how the inventor intended the function to be performed. Therefore, the claim lacks adequate written description
Dependent claims 2-10 and 12-19 are rejected due to their dependencies
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claims 1, 11 and 20 recites the 112(f) limitation "a voice clone detection bot." The specification does not provide a disclosure of the computer and algorithm in sufficient detail to demonstrate to one of ordinary skill in the art that the inventor possessed the invention. The specification describes the voice clone detection bot 12 only in terms of its functions without disclosing an algorithm or procedure for how the bot accomplishes these functions. For software, the algorithm or steps/procedure taken to perform the function must be described with sufficient detail so that one of ordinary skill in the art would understand how the inventor intended the function to be performed. Therefore, the claim lacks adequate written description.
Claim 4 and 14 recites "another vocoder from the one or more AI classifiers," however, no vocoder has been previously recited in claim 1, from which claim 4 depends. Because there is no antecedent basis for "another vocoder" in the claim or any claim from which it depends, the scope of this limitation is indefinite.
To overcome this rejection, Applicant should amend claim 4 to depend from claim 2, where "a set of vocoders" is first introduced, or alternatively introduce "a vocoder" earlier in claim 4 before referencing it.
Claim 6 and 16 recites the limitation "to make the audio file, under analysis," however, this phrase appears to be grammatically incomplete and fails to convey what action is being performed on the audio file. It is unclear whether the intended meaning is "to make the audio file available," "to make the audio file accessible," or some other operation entirely.
To overcome this rejection, Applicant should amend the phrase to complete the intended action.
Claim 7 and 17 recites "the computer of the user," however, claim 1, from which claim 7 depends, recites only "a computing device of the user." Because "the computer" lacks antecedent basis in the claim from which it depends, the scope of this limitation is indefinite.
To overcome this rejection, Applicant should amend "the computer of the user" to "the computing device of the user" to match the language of claim 1.
All dependent claims are further rejected due to their dependencies to the independent claims.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
Claims 1, 3-4, 6, 11, 13-14, 16 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. (US 20240005947 A1, referred to as Wang), in view of Enzinger et al. (US 20210193174 A1, referred to as Enzinger).
In reference to claim 1, A cyber security system to protect against cyber threats including a synthetic clone of a voice of a speaker (Wang: [0001] and [0016] Provides for a SSD system as a security protection mechanism against synthetic voice threats.)
A deep learning model trained to analyze an audio file input into the deep learning model and to produce as an output of one or more embeddings of the audio file, under analysis (Wang: [0056]-[0058] Provides for DNNs processing acoustic features and producing abstracted feature vectors through a pooling/embedding layer.)
One or more AI classifiers trained to analyze the one or more embeddings of the audio file, under analysis, from the deep learning model to determine whether it is likely that the voice of the speaker engaging with a user is real or the synthetic clone of the voice of the speaker (Wang: [0053]-[0055] and [0064] Provides for feed-forward classifiers operating on the pooled embedding vector to produce a probability score of synthetic vs. real speech maps.)
A voice clone detection bot configured to be resident on a computing device of the user and to integrate with different sources of audio data on the computing device of the user in order to collect the audio file containing an attempt to synthetically clone the voice of the speaker protected by the cyber security system (Wang: [0039]-[0043], [0062], and [0083] Provides for deploying the trained SSD model on end-user devices and receiving audio from microphones or media streams.)
Wang does not explicitly disclose that the voice detection system is a voice detection bot however, Enzinger discloses:
Wherein the voice detection system is a voice detection bot (Enzinger: [0004], [0031] and [0094] Provides for a tampering detector system specifically targeting voice synthesis and voice conversion.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang, which provides a cyber security system using deep learning models and AI classifiers to detect synthetic voice clones through analysis of audio embeddings on user computing devices, with the teachings of Enzinger, which introduces implementing the voice detection functionality as a specialized bot system targeting voice synthesis and conversion tampering. One of ordinary skill in the art would recognize the ability to incorporate Enzinger's bot architecture into Wang's voice clone detection system to provide automated, persistent monitoring capabilities. One of ordinary skill in the art would be motivated to make this modification in order to enable continuous, autonomous operation of the voice detection system without requiring constant user intervention.
In reference to claim 3, The cyber security system of claim 1, where a first AI classifier of the one or more AI classifiers is a speaker AI classifier trained to compare a current embedding of the audio file and its associated speaker from the deep learning model against one or more embeddings known to be from the speaker who is allegedly speaking in the audio file, under analysis (Wang: [0041] and [0055]-[0057] Provides for comparing synthetic speech against known real recordings of the same speaker, treating them as distinguishable identities.)
In reference to claim 4, The cyber security system of claim 1, further comprising: a binary AI classifier trained to receive 1) a determination of how likely a current embedding of the audio file and its associated speaker, under analysis, is actually the speaker or is the synthetic clone of the voice of the speaker, and 2) a determination of how likely the audio file, under analysis, was created by another vocoder from the one or more AI classifiers, and then to evaluate the determinations in order to determine when it is likely that the voice of the speaker engaging with the user in the audio file, under analysis, is real or fake (Wang: [0016]. [0053], [0064], [0097] Fig 3 and 6 Provides for multiple classifier determinations (speaker identity, channel/vocoder characteristics, and SSD probability) are collectively evaluated to reach a binary real/fake outcome.)
In reference to claim 6, The cyber security system of claim 1, where the voice clone detection bot is further configured to insert itself into one or more of a phone application, an online meeting application, or other voice driven application resident on the computing device of the user and then monitor that application, and when a conversation is happening in the application, then to make the audio file, under analysis, and supply the audio file, under analysis, to the deep learning model that is trained to analyze the audio file, under analysis (Enzinger: [0090]-[0095] Provides for On-device residency of the authentication service, monitoring of voice calls in progress, and supplying audio to a deep learning model.)
In reference to claim 11, Method for a cyber security system to protect against cyber threats including a synthetic clone of a voice of a speaker (Wang: [0001] and [0016] Provides for a SSD system as a security protection mechanism against synthetic voice threats.)
Providing a deep learning model trained to analyze an audio file input into the deep learning model and to produce as an output of one or more embeddings of the audio file, under analysis (Wang: [0056]-[0058] Provides for DNNs processing acoustic features and producing abstracted feature vectors through a pooling/embedding layer.)
Providing one or more AI classifiers trained to analyze the one or more embeddings of the audio file, under analysis, from the deep learning model to determine whether it is likely that the voice of the speaker engaging with a user is real or the synthetic clone of the voice of the speaker (Wang: [0053]-[0055] and [0064] Provides for feed-forward classifiers operating on the pooled embedding vector to produce a probability score of synthetic vs. real speech maps.)
Providing a voice clone detection bot configured to be resident on a computing device of the user and to integrate with different sources of audio data on the computing device of the user in order to collect the audio file containing an attempt to synthetically clone the voice of the speaker protected by the cyber security system (Wang: [0039]-[0043], [0062], and [0083] Provides for deploying the trained SSD model on end-user devices and receiving audio from microphones or media streams.)
Wang does not explicitly disclose that the voice detection system is a voice detection bot however, Enzinger discloses:
Wherein the voice detection system is a voice detection bot (Enzinger: [0004], [0031] and [0094] Provides for a tampering detector system specifically targeting voice synthesis and voice conversion.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang, which provides a cyber security system using deep learning models and AI classifiers to detect synthetic voice clones through analysis of audio embeddings on user computing devices, with the teachings of Enzinger, which introduces implementing the voice detection functionality as a specialized bot system targeting voice synthesis and conversion tampering. One of ordinary skill in the art would recognize the ability to incorporate Enzinger's bot architecture into Wang's voice clone detection system to provide automated, persistent monitoring capabilities. One of ordinary skill in the art would be motivated to make this modification in order to enable continuous, autonomous operation of the voice detection system without requiring constant user intervention.
In reference to claim 13, The method for the cyber security system of claim 11, further comprising: providing a first AI classifier of the one or more AI classifiers as a speaker AI classifier trained to compare a current embedding of the audio file and its associated speaker from the deep learning model against one or more embeddings known to be from the speaker who is allegedly speaking in the audio file, under analysis (Wang: [0041] and [0055]-[0057] Provides for comparing synthetic speech against known real recordings of the same speaker, treating them as distinguishable identities.)
In reference to claim 14, The method for the cyber security system of claim 11, further comprising: providing a binary AI classifier trained to receive 1) a determination of how likely a current embedding of the audio file and its associated speaker, under analysis, is actually the speaker or is the synthetic clone of the voice of the speaker, and 2) a determination of how likely the audio file, under analysis, was created by another vocoder from the one or more AI classifiers, and then to evaluate the determinations in order to determine when it is likely that the voice of the speaker engaging with the user in the audio file, under analysis, is real or fake (Wang: [0016]. [0053], [0064], [0097] Fig 3 and 6 Provides for multiple classifier determinations (speaker identity, channel/vocoder characteristics, and SSD probability) are collectively evaluated to reach a binary real/fake outcome.)
In reference to claim 16, The method for the cyber security system of claim 11, further comprising: providing the voice clone detection bot to insert itself into one or more of a phone application, an online meeting application, or other voice driven application resident on the computing device of the user and then monitor that application, and when a conversation is happening in the application, then to make the audio file, under analysis, and supply the audio file, under analysis, to the deep learning model that is trained to analyze the audio file, under analysis (Enzinger: [0090]-[0095] Provides for On-device residency of the authentication service, monitoring of voice calls in progress, and supplying audio to a deep learning model.)
In reference to claim 20, A non-transitory memory storage device to store instructions in an executable format to be executed by one or more processors, which when executed are configured to cause a computing device to perform operations as follows (Wang: [0001] and [0016] Provides for a SSD system as a security protection mechanism against synthetic voice threats.)
Using a deep learning model trained to analyze an audio file input into the deep learning model and to produce as an output of one or more embeddings of the audio file, under analysis (Wang: [0056]-[0058] Provides for DNNs processing acoustic features and producing abstracted feature vectors through a pooling/embedding layer.)
Using one or more AI classifiers trained to analyze the one or more embeddings of the audio file, under analysis, from the deep learning model to determine whether it is likely that the voice of the speaker engaging with a user is real or the synthetic clone of the voice of the speaker (Wang: [0053]-[0055] and [0064] Provides for feed-forward classifiers operating on the pooled embedding vector to produce a probability score of synthetic vs. real speech maps.)
Using a voice clone detection bot configured to be resident on a computing device of the user and to integrate with different sources of audio data on the computing device of the user in order to collect the audio file containing an attempt to synthetically clone the voice of the speaker protected by the cyber security system (Wang: [0039]-[0043], [0062], and [0083] Provides for deploying the trained SSD model on end-user devices and receiving audio from microphones or media streams.)
Wang does not explicitly disclose that the voice detection system is a voice detection bot however, Enzinger discloses:
Wherein the voice detection system is a voice detection bot (Enzinger: [0004], [0031] and [0094] Provides for a tampering detector system specifically targeting voice synthesis and voice conversion.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang, which provides a cyber security system using deep learning models and AI classifiers to detect synthetic voice clones through analysis of audio embeddings on user computing devices, with the teachings of Enzinger, which introduces implementing the voice detection functionality as a specialized bot system targeting voice synthesis and conversion tampering. One of ordinary skill in the art would recognize the ability to incorporate Enzinger's bot architecture into Wang's voice clone detection system to provide automated, persistent monitoring capabilities. One of ordinary skill in the art would be motivated to make this modification in order to enable continuous, autonomous operation of the voice detection system without requiring constant user intervention.
Claims 2, 5, 12 and 15 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. (US 20240005947 A1, referred to as Wang), in view of Enzinger et al. (US 20210193174 A1, referred to as Enzinger) in further view of Tzoreff (US 20250022473 A1, referred to as Tzoreff).
In reference to claim 2, The cyber security system of claim 1, where a first AI classifier of the one or more AI classifiers is a vocoder identification classifier trained on characteristics of a set of vocoders to predict whether at least one of 1) a particular vocoder in that set of vocoders and 2) a type of vocoder in that set of vocoders that was used to generate the synthetic clone of the voice of the speaker in the audio file, under analysis (Tzoreff: [0015]-[0018] Provides for repeatedly identifying vocoders as the mechanism of synthetic voice generation and discloses classifiers trained to detect vocoder generated audio by analyzing vocoder artifacts and characteristics.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Tzoreff, which introduces a specialized vocoder identification classifier trained to detect specific vocoders or vocoder types used in synthetic voice generation. One of ordinary skill in the art would recognize the ability to incorporate Tzoreff's vocoder-specific classification into the combined voice clone detection system to enhance detection capabilities through targeted analysis of vocoder artifacts. One of ordinary skill in the art would be motivated to make this modification in order to improve detection accuracy by identifying the specific synthesis techniques used to create fake voices.
In reference to claim 5, The cyber security system of claim 1, further comprising: a deepfake detector module configured to determine whether 1) at least one of a phone call session and an online meeting session is still in progress and 2) the voice of the speaker engaging with the user is actually determined to be the synthetic clone of the voice of the speaker, then the deepfake detector module is configured to send a message to the user indicating a deepfake has been detected via the voice clone detection bot (Tzoreff: [0023] and [0036]-[0037] Provides for a system that monitors an ongoing communication session (telephone call), makes a determination that the speaker is a synthetic voice, and then sends an alerting message to the user/target indicating a deepfake has been detected.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Tzoreff, which introduces a deepfake detector module that monitors ongoing communication sessions and sends real-time alerts to users when synthetic voices are detected during active calls or meetings. One of ordinary skill in the art would recognize the ability to incorporate Tzoreff's real-time session monitoring and alerting capabilities into the combined voice clone detection system to provide immediate user protection. One of ordinary skill in the art would be motivated to make this modification in order to enable proactive user warning during active communication sessions before users can be deceived or manipulated.
In reference to claim 12,The method for the cyber security system of claim 11, further comprising: providing a first AI classifier of the one or more AI classifiers as a vocoder identification classifier trained on characteristics of a set of vocoders to predict whether at least one of 1) a particular vocoder in that set of vocoders and 2) a type of vocoder in that set of vocoders that was used to generate the synthetic clone of the voice of the speaker in the audio file, under analysis (Tzoreff: [0015]-[0018] Provides for repeatedly identifying vocoders as the mechanism of synthetic voice generation and discloses classifiers trained to detect vocoder generated audio by analyzing vocoder artifacts and characteristics.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Tzoreff, which introduces a specialized vocoder identification classifier trained to detect specific vocoders or vocoder types used in synthetic voice generation. One of ordinary skill in the art would recognize the ability to incorporate Tzoreff's vocoder-specific classification into the combined voice clone detection system to enhance detection capabilities through targeted analysis of vocoder artifacts. One of ordinary skill in the art would be motivated to make this modification in order to improve detection accuracy by identifying the specific synthesis techniques used to create fake voices.
In reference to claim 15, The method for the cyber security system of claim 11, further comprising: providing a deepfake detector module to determine whether 1) at least one of a phone call session and an online meeting session is still in progress and 2) the voice of the speaker engaging with the user is actually determined to be the synthetic clone of the voice of the speaker, then to send a message to the user indicating a deepfake has been detected via the voice clone detection bot (Tzoreff: [0023] and [0036]-[0037] Provides for a system that monitors an ongoing communication session (telephone call), makes a determination that the speaker is a synthetic voice, and then sends an alerting message to the user/target indicating a deepfake has been detected.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Tzoreff, which introduces a deepfake detector module that monitors ongoing communication sessions and sends real-time alerts to users when synthetic voices are detected during active calls or meetings. One of ordinary skill in the art would recognize the ability to incorporate Tzoreff's real-time session monitoring and alerting capabilities into the combined voice clone detection system to provide immediate user protection. One of ordinary skill in the art would be motivated to make this modification in order to enable proactive user warning during active communication sessions before users can be deceived or manipulated.
Claims 7 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. (US 20240005947 A1, referred to as Wang), in view of Enzinger et al. (US 20210193174 A1, referred to as Enzinger) in further view of Traynor et al. (US 20220036904 A1, referred to as Traynor).
In reference to claim 7, The cyber security system of claim 1, further comprising: an audio preprocessing stage configured to receive the audio file, under analysis, from the computer of the user and then to perform audio preprocessing including splitting the audio file, under analysis, into individual sentences and then to organize audio chunk files by each speaker detected in the audio file, under analysis (Traynor: [0057]-[0058] and [0065]-[0068] Provides for an audio preprocessing stage that segments audio files into discrete units and organizes those segments on a per-speaker basis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Traynor, which introduces an audio preprocessing stage that segments audio files into individual sentences and organizes audio chunks by speaker. One of ordinary skill in the art would recognize the ability to incorporate Traynor's preprocessing capabilities into the combined voice clone detection system to improve analysis accuracy through structured audio segmentation. One of ordinary skill in the art would be motivated to make this modification in order to enable more precise detection by analyzing coherent speech units rather than raw continuous audio streams.
In reference to claim 17, The method for the cyber security system of claim 11, further comprising: providing an audio preprocessing stage to receive the audio file, under analysis, from the computer of the user and then to perform audio preprocessing including splitting the audio file, under analysis, into individual sentences and then to organize audio chunk files by each speaker detected in the audio file, under analysis (Traynor: [0057]-[0058] and [0065]-[0068] Provides for an audio preprocessing stage that segments audio files into discrete units and organizes those segments on a per-speaker basis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Traynor, which introduces an audio preprocessing stage that segments audio files into individual sentences and organizes audio chunks by speaker. One of ordinary skill in the art would recognize the ability to incorporate Traynor's preprocessing capabilities into the combined voice clone detection system to improve analysis accuracy through structured audio segmentation. One of ordinary skill in the art would be motivated to make this modification in order to enable more precise detection by analyzing coherent speech units rather than raw continuous audio streams.
Claims 8 and 18 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. (US 20240005947 A1, referred to as Wang), in view of Enzinger et al. (US 20210193174 A1, referred to as Enzinger) in further view of Jin et al. (US 20210256978 A1, referred to as Jin).
In reference to claim 8, The cyber security system of claim 1, where the voice clone detection bot is configured to cooperate with a user interface to allow the user of the computing device to manually press an upload button to upload a desired audio file that the user has stored on the computing device as the audio file, under analysis (Jin: [0039]-[0047] Provides for a user facing portal interface on a client device through which a user manually submits a stored audio file for analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Jin, which introduces a user interface that allows manual submission of stored audio files through an upload button. One of ordinary skill in the art would recognize the ability to incorporate Jin's user-controlled upload functionality into the combined voice clone detection bot to provide on-demand analysis capabilities. One of ordinary skill in the art would be motivated to make this modification in order to give users the flexibility to analyze suspicious audio files they have already received or saved.
In reference to claim 18, The method for the cyber security system of claim 11, further comprising: providing the voice clone detection bot to cooperate with a user interface to allow the user of the computing device to manually press an upload button to upload a desired audio file that the user has stored on the computing device as the audio file, under analysis (Jin: [0039]-[0047] Provides for a user facing portal interface on a client device through which a user manually submits a stored audio file for analysis.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Jin, which introduces a user interface that allows manual submission of stored audio files through an upload button. One of ordinary skill in the art would recognize the ability to incorporate Jin's user-controlled upload functionality into the combined voice clone detection bot to provide on-demand analysis capabilities. One of ordinary skill in the art would be motivated to make this modification in order to give users the flexibility to analyze suspicious audio files they have already received or saved.
Claims 9 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. (US 20240005947 A1, referred to as Wang), in view of Enzinger et al. (US 20210193174 A1, referred to as Enzinger) in further view of Mirsky (US 20250112988 A1, referred to as Mirsky).
In reference to claim 9, The cyber security system of claim 1, further comprising: a deepfake detector module configured to determine whether at least one of a phone call session, an online meeting session is still in progress and the voice of the speaker engaging with the user is actually the synthetic clone of the voice of the speaker, then the deepfake detector module is configured to cause the application in which the detected synthetic clone of the voice of the speaker is occurring in to shut down (Mirsky: [0068]-[0072], [0103] and [0136] Provides for a detection module that monitors active call and online meeting sessions and upon confirming a synthetic clone is present executes a termination response.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Mirsky, which introduces a deepfake detector module that monitors active communication sessions and automatically terminates applications when synthetic voices are detected. One of ordinary skill in the art would recognize the ability to incorporate Mirsky's automated termination capabilities into the combined voice clone detection system to provide immediate protective action. One of ordinary skill in the art would be motivated to make this modification in order to prevent users from being deceived or manipulated by automatically ending suspicious communications before harm can occur.
In reference to claim 19, The method for the cyber security system of claim 11, further comprising: providing a deepfake detector module to determine whether at least one of a phone call session, an online meeting session is still in progress and the voice of the speaker engaging with the user is actually the synthetic clone of the voice of the speaker, then to cause the application in which the detected synthetic clone of the voice of the speaker is occurring in to shut down (Mirsky: [0068]-[0072], [0103] and [0136] Provides for a detection module that monitors active call and online meeting sessions and upon confirming a synthetic clone is present executes a termination response.)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Mirsky, which introduces a deepfake detector module that monitors active communication sessions and automatically terminates applications when synthetic voices are detected. One of ordinary skill in the art would recognize the ability to incorporate Mirsky's automated termination capabilities into the combined voice clone detection system to provide immediate protective action. One of ordinary skill in the art would be motivated to make this modification in order to prevent users from being deceived or manipulated by automatically ending suspicious communications before harm can occur.
Claim 10 rejected under 35 U.S.C. 103 as being unpatentable over Wang et al. (US 20240005947 A1, referred to as Wang), in view of Enzinger et al. (US 20210193174 A1, referred to as Enzinger) in further view of Slocum et al. (US 20230260521 A1, referred to as Slocum).
In reference to claim 10, The cyber security system of claim 1, further comprising: a synthetic voice generation system configured to generate synthetic voice data in a self-supervised manner for a training of the user to detect when the synthetic cloning of the voice of the speaker is occurring (Slocum: [0051]-[0053] Provides for self-supervised training using synthetically generated voice data (TTS/VC).)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the teachings of Wang in view of Enzinger, which together provide a bot-based cyber security system using deep learning and AI classifiers to detect synthetic voice clones, with the teachings of Slocum, which introduces a synthetic voice generation system for creating training data in a self-supervised manner to help users learn to recognize voice cloning. One of ordinary skill in the art would recognize the ability to incorporate Slocum's self-supervised training approach into the combined voice clone detection system to enhance user awareness and detection capabilities. One of ordinary skill in the art would be motivated to make this modification in order to provide users with practical training experience in recognizing synthetic voices by exposing them to controlled examples.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. See PTO-892.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to AIDAN EDWARD SHAUGHNESSY whose telephone number is (703)756-1423. The examiner can normally be reached on Monday-Friday from 7:30am to 5pm.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Jeffrey Nickerson, can be reached at telephone number (469) 295-9235. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from Patent Center and the Private Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from Patent Center or Private PAIR. Status information for unpublished applications is available through Patent Center and Private PAIR for authorized users only. Should you have questions about access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free).
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) Form at https://www.uspto.gov/patents/usptoautomated-interview-request-air-form.
/A.E.S./Examiner, Art Unit 2432
/Jeffrey Nickerson/Supervisory Patent Examiner, Art Unit 2432
Prosecution Insights