DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
The amendment filed 7/27/2026 has been placed of record in the file.
Claims 1, 9, and 10 have been amended.
Claims 18-20 have been canceled.
Claims 21-23 have been added.
Claims 1-17 and 21-23 are now pending.
The double patenting rejection remains of record.
Claim 10 remains objected to as described in the rejection dated 2/26/2026.
The applicant’s arguments with respect to claims 1-17 and 21-23 have been considered but are moot in view of the following new grounds of rejection.
Response to Amendment
Claims have been amended to further define the process for generating the score. The amendment proves a change in scope to the independent claims as the independent claims now explicitly state generating the score based on semantic matching distance, matching degree score, etc. However, none of the amended claims show a patentable distinction over the prior art as evidenced by the following new grounds of rejection.
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 1-6, 8, 9, 14-17, and 22 are rejected under 35 U.S.C. 103 as being unpatentable over Boyer et al. (U.S. Patent Application Publication Number 2024/0414211), hereinafter referred to as Boyer, in view of Cho et al. (U.S. Patent Application Publication Number 2025/0016182), hereinafter referred to as Cho.
Boyer disclosed techniques for utilizing LLMs in cooperation with cybersecurity components. In an analogous art, Cho disclosed techniques for detecting and analyzing time-series data with a cyber threat framework. Both systems are directed toward cyber threat detection.
Regarding claim 1, Boyer discloses a non-transitory computer-readable data storage medium storing program code executable by a processor to perform processing comprising: selecting anomalies regarding a specified entity that occurred within a specified time period, from a plurality of anomalies identified by security analysis performed on a plurality of raw events regarding a plurality of entities including the specified entity (paragraph 94, detects anomalous behavior, and paragraph 97, given timeframe); enhancing the selected anomalies with additional information regarding the selected anomalies (paragraph 97, factoring additional data points); evaluating the selected anomalies, as have been enhanced with the additional information, against a database of security threats to identify the security threats that the selected anomalies are related to (paragraph 97, see if correlation exists between anomalies and threats); respectively generating scores for the identified security threats that the selected anomalies are related to, by generating the score for each identified security threat using a function (paragraph 178, score that process is malicious); selecting a subset of the identified security threats that the selected anomalies are related to, based on the scores (paragraph 179, threat level posed to be used for ranking, and paragraph 184, outputs supported threats); generating, based on the selected anomalies as have been enhanced with the additional information and based on the selected subset of the identified security threats, a prompt to input to a large language model (LLM), the prompt generated to solicit a response from the LLM including a natural language summary associating the identified security threats with the selected anomalies regarding the specified entity that occurred within the specified time period (paragraph 45, LLM performs summarization and prioritization of breaches, and paragraph 26, Natural Language Processing); providing the generated prompt as input to the LLM (paragraph 45, summarization of input); receiving the response as output from the LLM (paragraph 46, produces and presents information); and performing an action related to the identified security threats based on the received response (paragraph 117, remediation actions).
Boyer does not explicitly state the function based on one or more than one of: a minimum semantic matching distance of the identified security threat to the selected anomalies, an average matching degree score of the security threat as identified via evaluation against the database of the security threats as compared to calling an application programming interface (API) for a knowledge base of the security threats, and a maximum probability of importance of the identified security threat for the specified entity within the specified time period. However, analyzing threats in such a fashion was well known in the art as evidenced by Cho. Since the inventions encompass the same field of endeavor, 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 system of Boyer by adding the ability for the function based on an average matching degree score of the security threat as identified via evaluation against the database of the security threats as compared to calling an application programming interface (API) for a knowledge base of the security threats as provided by Cho (see paragraph 72, degree of matching between threat behavior type and target API event). One of ordinary skill in the art would have recognized the benefit that generating a risk score in this way would assist in responding to cyber security threats that are changing and evolving (see Cho, paragraph 10).
Regarding claim 2, the combination of Boyer and Cho discloses wherein performing the action comprises outputting the natural language summary associating the identified security threats with the selected anomalies with the selected anomalies regarding the specified entity that occurred within the specified time period (Boyer, paragraph 26, human readable and understandable output).
Regarding claim 3, the combination of Boyer and Cho discloses wherein and wherein performing the action comprises resolving or limiting an impact of the identified security threats at the specified entity (Boyer, paragraph 117, remediation actions).
Regarding claim 4, the combination of Boyer and Cho discloses wherein resolving or limiting the impact of the identified security comprises either or both of: reconfiguring the specified entity to resolve the identified security threats (Boyer, paragraph 117, restores node); quarantining the specified entity to limit the impact of the identified security threats.
Regarding claim 5, the combination of Boyer and Cho discloses wherein enhancing the selected anomalies with the additional information comprises: retrieving the raw events related to the selected anomalies and on which basis the security analysis identified the selected anomalies; and including the retrieved raw events within the additional information regarding the selected anomalies (Boyer, paragraph 130, behavior pattern data).
Regarding claim 6, the combination of Boyer and Cho discloses wherein the anomalies that have been identified by the security analysis include process anomalies that each specify a process that has been executing on the specified entity (Boyer, paragraph 96, identify and track processes).
Regarding claim 8, the combination of Boyer and Cho discloses wherein enhancing the selected anomalies with the additional information comprises, for the process specified by each process anomaly: retrieving information regarding one or more of: a process hierarchy of the process, including either or both of a parent process and a grandparent process of the process that have also been executing on the specified entity; an importance level of the process (Boyer, paragraph 58, criticality of incident); a description of the process; a command-line instruction used to invoke the process; an amount of time that the process has been executing on the specified entity; and/or an amount of time that the process has been executing on an entity group including the specified entity; and including the retrieved information within the additional information regarding the selected anomalies.
Regarding claim 9, the combination of Boyer and Cho discloses wherein the function is further based on: a total number of the selected anomalies that are related to the identified security threat; and a total number of the process anomalies included in the selected anomalies that are related to the identified security threat (Boyer, paragraph 59, number of breaches at varying severity scores).
Regarding claim 14, the combination of Boyer and Cho discloses wherein generating the prompt to input to the LLM is generated based on the selected anomalies as have been enhanced with the additional information and based on the selected subset of the identified security threats comprises: generating the prompt based on a natural language summary synthesizing the selected anomalies that occurred within the specified time period and based on the selected subset of the identified security threats (Boyer, paragraph 26, technical cyber security format).
Regarding claim 15, the combination of Boyer and Cho discloses wherein the processing further comprises: generating the natural language summary synthesizing the selected anomalies that occurred within the specified time period (Boyer, paragraph 97, given timeframe).
Regarding claim 16, the combination of Boyer and Cho discloses wherein the prompt is a third prompt, the response is a third response, the LLM is a third LLM, and generating the natural language summary synthesizing the selected anomalies comprises: generating, based on the selected anomalies as have been enhanced with the additional information, a second prompt to input to a second LLM, the prompt generated to solicit a second response from the second LLM including the natural language summary synthesizing the selected anomalies; providing the generated second prompt as input to the second LLM; and receiving the second response as output from the second LLM (Boyer, paragraph 45, LLM performs summarization and prioritization of breaches, and paragraph 26, Natural Language Processing, and paragraph 45, multiple LLMs).
Regarding claim 17, the combination of Boyer and Cho discloses wherein the third LLM and the second LLM are a same LLM, or the third LLM and the second LLM are different LLMs (Boyer, paragraph 45, multiple LLMs).
Regarding claim 22, the combination of Boyer and Cho discloses wherein the function is based on at least the average matching degree score of the security threat as identified via evaluation against the database of the security threats as compared to calling the API for the knowledge base of the security threats (Cho, paragraph 72, degree of matching between threat behavior type and target API event).
Claim 7 is rejected under 35 U.S.C. 103 as being unpatentable over Boyer in view of Cho, further in view of Manhas et al. (U.S. Patent Application Publication Number 2024/0163294), hereinafter referred to as Manhas.
The combination of Boyer and Cho disclosed techniques for utilizing LLMs in cooperation with cybersecurity components. In an analogous art, Manhas disclosed techniques for detecting and analyzing malicious flows. Both systems are directed toward cyber threat detection.
Regarding claim 7, the combination of Boyer and Cho discloses wherein enhancing the selected anomalies with the additional information comprises, for the process specified by each process anomaly: calling an application programming interface (API) for a knowledge base of the security threats to retrieve information regarding the security threats that the process is related to; and including the retrieved information regarding the security threats that the process is related to within the additional information regarding the selected anomalies (Boyer, paragraph 108, extracts data from data store).
The combination of Boyer and Cho does not explicitly state calling the knowledge base based on a hash of the process. However, utilizing a hash in such a fashion was well known in the art as evidenced by Manhas. Since the inventions encompass the same field of endeavor, 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 combination of Boyer and Cho by adding the ability for calling the knowledge base based on a hash of the process as provided by Manhas (see paragraph 57, provides process hash to threat detection module). One of ordinary skill in the art would have recognized the benefit that utilizing the process hash in this way would assist in providing additional metadata for intrusion detection systems (see Manhas, paragraph 1).
Claims 11-13 and 21 are rejected under 35 U.S.C. 103 as being unpatentable over Boyer in view of Cho, further in view of Bulut et al. (U.S. Patent Application Publication Number 2024/0427879), hereinafter referred to as Bulut.
The combination of Boyer and Cho disclosed techniques for utilizing LLMs in cooperation with cybersecurity components. In an analogous art, Bulut disclosed techniques for using an LLM for combining security data with natural language text. Both systems are directed toward cyber threat detection.
Regarding claim 11, the combination of Boyer and Cho does not explicitly state wherein evaluating the selected anomalies, as have been enhanced with the additional information, against the database of the security threats comprises, for each selected anomaly: generating an embedding vector capturing a semantic representation of the selected anomaly as has been enhanced with the additional information; querying the database using the embedding vector to identify, as the security threats that the selected anomaly is related to, a number of the security threats satisfying a matching criterion; and receiving, when querying the database using the embedding vector, a semantic matching distance between the embedding vector and each of the number of the security threats satisfying the matching criterion. However, utilizing an embedding vector in such a fashion was well known in the art as evidenced by Bulut. Since the inventions encompass the same field of endeavor, 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 combination of Boyer and Cho by adding the ability that evaluating the selected anomalies, as have been enhanced with the additional information, against the database of the security threats comprises, for each selected anomaly: generating an embedding vector capturing a semantic representation of the selected anomaly as has been enhanced with the additional information; querying the database using the embedding vector to identify, as the security threats that the selected anomaly is related to, a number of the security threats satisfying a matching criterion; and receiving, when querying the database using the embedding vector, a semantic matching distance between the embedding vector and each of the number of the security threats satisfying the matching criterion as provided by Bulut (see paragraph 98, user query embeddings for identifying threats, and paragraph 22, matches and retrieves relevant security data). One of ordinary skill in the art would have recognized the benefit that utilizing embeddings in this way would assist in enhancing the retrieval and analysis of security related data (see Bulut, paragraph 19).
Regarding claim 12, the combination of Boyer, Cho, and Bulut discloses wherein the database is an embedding vector database of embedding vectors for the security threats, and wherein the embedding vector for each security threat captures a semantic representation of information regarding the security threat within a knowledge base of the security threats (Bulut, paragraph 23, embeddings are semantically meaningful).
Regarding claim 13, the combination of Boyer, Cho, and Bulut discloses wherein generating the embedding vector for each selected anomaly comprises applying a specified embedding model to the selected anomaly, and wherein the embedding vector for each security threat is generated by applying the specified embedding model to the information regarding the security threat within the knowledge base (Bulut, paragraph 98, loglines filtered based on limitations of model).
Regarding claim 21, the combination of Boyer and Cho does not explicitly state wherein the function is based on at least the minimum semantic matching distance of the identified security threat to the selected anomalies. However, analyzing threats in such a fashion was well known in the art as evidenced by Bulut. Since the inventions encompass the same field of endeavor, 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 combination of Boyer and Cho by adding the ability that the function is based on at least the minimum semantic matching distance of the identified security threat to the selected anomalies as provided by Bulut (see paragraph 21, identifying relevant loglines based on embedding distances, and paragraph 23, embeddings are semantically meaningful). One of ordinary skill in the art would have recognized the benefit that utilizing embeddings in this way would assist in enhancing the retrieval and analysis of security related data (see Bulut, paragraph 19).
Claim 23 is rejected under 35 U.S.C. 103 as being unpatentable over Boyer in view of Cho, further in view of Rajasekharan et al. (U.S. Patent Application Publication Number 2019/0044963), hereinafter referred to as Rajasekharan.
The combination of Boyer and Cho disclosed techniques for utilizing LLMs in cooperation with cybersecurity components. In an analogous art, Rajasekharan disclosed techniques for identifying insider threats. Both systems are directed toward cyber threat detection.
Regarding claim 23, the combination of Boyer and Cho does not explicitly state wherein the function is based on at least the maximum probability of importance of the identified security threat for the specified entity within the specified time period. However, analyzing threats in such a fashion was well known in the art as evidenced by Rajasekharan. Since the inventions encompass the same field of endeavor, 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 combination of Boyer and Cho by adding the ability that the function is based on at least the maximum probability of importance of the identified security threat for the specified entity within the specified time period as provided by Rajasekharan (see paragraph 21, importance probabilities). One of ordinary skill in the art would have recognized the benefit that generating a risk score in this way would assist in detecting suspicious activity (see Rajasekharan, paragraph 1).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Victor Lesniewski whose telephone number is (571)272-2812. The examiner can normally be reached Monday thru Friday, 9am to 5pm.
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) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Carl Colin can be reached at 571-272-3862. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/Victor Lesniewski/Primary Examiner, Art Unit 2493