DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
2. Claims 1-10 are pending. Claims 1 and 9 are in independent forms.
Priority
3. Foreign priority has been claimed to JP application # 2023-093513 filed on 6/06/2023.
Information Disclosure Statement
4. The information disclosure statements (IDS's) submitted on 07/02/2025 is in compliance with provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Drawings
5. The drawings filed on 06/04/2025 are accepted by the examiner.
Claim Rejections - 35 USC § 112
6. 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.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
7. Claim 10 recites : “a non-transitory computer-readable recording medium for use in a computer, the recording medium having recorded thereon a computer program for causing the computer to execute the program identification method according to claim 1”.
Claim 1 recites: “a program identification method comprising:
obtaining….
generating….
converting….
outputting…..”
When claim 1 is rejoined with claim 10, the whole claim creates antecedent basis issue. Appropriate correction is necessary.
Claim Rejections - 35 USC § 103
8. 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.
9. Claims 1-6 and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Koli “RanDroid: Android Malware Detection Using Random Machine Learning Classifier (hereinafter Koli) in view of Lee US Patent Application Publication No. 2018/0052829 (hereinafter Lee).
Regarding claim 1, Koli discloses a program identification method comprising:
obtaining a machine learning model generated through training with use of
labeled training data indicating whether each of first programs is malicious (see Koli Fig. 5, page 4, lines 4-10, Phase IV aims at modeling the classifiers by training four supervised machine learning algorithms; SVM, RF, DT and NB with the binary vectors of the sample apps. In supervised learning pre-labelled data is used to train the system. The annotated data is read by the system then memorized and then that data is used to distinguish alike malware), wherein:
“each of the first programs is expressed in a first language” (see Koli page 3, 8-11, Phase I is the process of reverse engineering where, the apps apk files were decompiled into their source code in the forms of AndroidManifest.xml and java classes by using Androguard malware analysis tool [10]);
“the machine learning model is generated through training with use of training data including first feature vectors and identification information items, each of the first feature vectors being obtained by extracting a feature of a different one of the first programs, each of the identification information items indicating whether a corresponding one of the first programs is malicious” (see Koli, page 4, lines 12- 21, In training phase, a set of features are parsed and extracted from the source code of a training set sample of malware and Goodware apps; The extracted features are then represented in binary vector format; next the set of binary vector of apps along with label information is passed into learning module where various machine learning algorithms are trained with the data set to build classification model.); and
“each of the first feature vectors is expressed in a first format indicating whether each of first functions of a program expressed in the first language is to be used by the corresponding one of the first programs” (see Koli page 3, line 34-page 4, line 2, If a particular api call/permission/presence of key feature is present in the application, then the corresponding features xi is defined as 1 otherwise as 0); and
“(iv) outputting an identification result indicating whether the second program is malicious, the identification result being obtained by inputting, to the machine learning model, the second feature vector whose format has been converted into the first format” (see Koli, page 4, lines 21- 27, In the prediction phase, the same set of features are extracted from source code and binary vector is generated for testing set sample of goodware and malware. Then generated binary vector is passed into classifier module where classification happens with the help of classification models built in the training phase. The result is available in the form of predicted label as Goodware or Malware);
Koli does not explicitly discloses (ii) generating a second feature vector by extracting a feature of a second program expressed in a second language different from the first language;
wherein the second feature vector is expressed in a second format indicating whether each of second functions of a program expressed in the second language is to be used by the second program; (iii) converting a format of the second feature vector generated into the first format.
However, in analogues art, Lee discloses (ii) generating a second feature vector by extracting a feature of a second program expressed in a second language different from the first language (see Lee par. 0013, generating, at a processor, a feature vector of a source sentence, wherein the source sentence may be written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a target sentence, wherein the target sentence may be written in a second language; and generating, at the processor, a normalized sentence from the feature vector of the target sentence by transforming the target sentence); wherein the second feature vector is expressed in a second format indicating whether each of second functions of a program expressed in the second language is to be used by the second program (see Lee par. 0102, the decoder decodes the embedding vector of the normalized sentence and generates a target sentence written in a second language. The decoder translates the normalized sentence written in the first language into the target sentence written in the second language); (iii) converting a format of the second feature vector generated into the first format (see Lee par. 0106, The decoder decodes the feature vector of the source sentence and generates a target sentence written in a second language. A normalization layer included in the decoder converts the target sentence to a normalized sentence. For example, the normalization layer in the decoder converts a feature vector of the target sentence to a feature vector of the normalized sentence, and the decoder outputs a final target sentence based on the feature vector of the normalized sentence).
Therefore it would have been obvious to a person of ordinary skill in the art before the effective filing date of the application to incorporate the teachings of Lee into the system of Koli to generate, at a processor, a feature vector of a source sentence, wherein the source sentence may be written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a normalized sentence; and generating, at the processor, a target sentence from the feature vector of the normalized sentence, wherein the target sentence corresponds to the source sentence and may be written in a second language (see Lee par. 0006).
Regarding claim 2, Koli in view of Lee discloses the program identification method according to claim 1,
Lee further discloses wherein in the converting, the format of the second feature vector is converted into the first format using a correspondence between the first functions and the second functions (see Lee par. 0130, the machine translation method performed by the machine translation apparatus includes generating a feature vector of a source sentence written in a first language from the source sentence, converting the feature vector of the source sentence to a feature vector of a target sentence that corresponds to the source sentence and that is written in a second language, and generating a normalized sentence from the feature vector of the target sentence).
Therefore it would have been obvious to a person of ordinary skill in the art before the effective filing date of the application to incorporate the teachings of Lee into the system of Koli to generate, at a processor, a feature vector of a source sentence, wherein the source sentence may be written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a normalized sentence; and generating, at the processor, a target sentence from the feature vector of the normalized sentence, wherein the target sentence corresponds to the source sentence and may be written in a second language (see Lee par. 0006).
Regarding claim 3, Koli in view of Lee discloses the program identification method according to claim 2,
Lee further discloses wherein the correspondence indicates that one first function among the first functions is associated with one second function among the second functions (see Lee par. 0017, a processor configured to generate a feature vector of a source sentence, convert the generated feature vector of the source sentence to a feature vector of a normalized sentence, and generate a target sentence from the feature vector of the normalized sentence, based on the neural network, wherein the source sentence may be written in a first language, and the target sentence corresponding to the source sentence may be written in a second language).
Therefore it would have been obvious to a person of ordinary skill in the art before the effective filing date of the application to incorporate the teachings of Lee into the system of Koli to generate, at a processor, a feature vector of a source sentence, wherein the source sentence may be written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a normalized sentence; and generating, at the processor, a target sentence from the feature vector of the normalized sentence, wherein the target sentence corresponds to the source sentence and may be written in a second language (see Lee par. 0006).
Regarding claim 4, Koli in view of Lee discloses the program identification method according to claim 3,
Lee further discloses wherein the correspondence indicates that other two or more first functions among the first functions excluding the one first function are associated with one other second function among the second functions excluding the one second function (see Lee par. 0093, the normalized sentence is a sentence generated by transforming the source sentence to include any one or any combination of any two or more of a vocabulary, a morpheme or a symbol omitted from the source sentence without distorting the meaning of the source sentence. In another example, the normalized sentence is generated by transforming the source sentence through substitution of any one or any combination of any two or more of a morpheme, a vocabulary, a word or a phrase included in the source sentence without distorting the meaning of the source sentence. In still another example, the normalized sentence is a sentence generated by changing word spacing in the source sentence, without distorting the meaning of the source sentence. In a further example, the normalized sentence is a sentence generated by changing a word order in the source sentence, without distorting the meaning of the source sentence).
Therefore it would have been obvious to a person of ordinary skill in the art before the effective filing date of the application to incorporate the teachings of Lee into the system of Koli to generate, at a processor, a feature vector of a source sentence, wherein the source sentence may be written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a normalized sentence; and generating, at the processor, a target sentence from the feature vector of the normalized sentence, wherein the target sentence corresponds to the source sentence and may be written in a second language (see Lee par. 0006).
Regarding claim 5, Koli in view of Lee discloses the program identification method according to claim 4,
Lee further discloses wherein the correspondence includes a weight of the one other second function assigned for the other two or more first functions (see Lee par. 0115, The training of the normalization layer 610 is a determination of a weight or a parameter of a neural network including the normalization layer 610. The trained normalization layer 610 is inserted as a normalization layer in the neural networks of FIGS. 4 and 5, to transform a source sentence or a target sentence to a normalized sentence).
Therefore it would have been obvious to a person of ordinary skill in the art before the effective filing date of the application to incorporate the teachings of Lee into the system of Koli to generate, at a processor, a feature vector of a source sentence, wherein the source sentence may be written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a normalized sentence; and generating, at the processor, a target sentence from the feature vector of the normalized sentence, wherein the target sentence corresponds to the source sentence and may be written in a second language (see Lee par. 0006).
Regarding claim 6, Koli in view of Lee discloses the program identification method according to claim 2,
Koli further discloses wherein the correspondence indicates a similarity between a vector representation of each of the first functions and a vector representation of each of the second functions (see Koli, page 4, lines 21- 27, In the prediction phase, the same set of features are extracted from source code and binary vector is generated for testing set sample of goodware and malware. Then generated binary vector is passed into classifier module where classification happens with the help of classification models built in the training phase. The result is available in the form of predicted label as Goodware or Malware).
Regarding claim 9, Koli discloses a program identification device comprising:
“a processor” (see Koli Fig. 1, page 2, lines 9-12, The first layer, the Linux Kernel layer is the most important layer and located at the bottom; it is responsible for hardware abstraction and drivers, security, file management, process management, and memory management); and
Memory (memory management), wherein using the memory, the processor:
“obtains a machine learning model generated through training with use of labeled training data indicating whether each of first programs is malicious” (see Koli Fig. 5, page 4, lines 4-10, Phase IV aims at modeling the classifiers by training four supervised machine learning algorithms; SVM, RF, DT and NB with the binary vectors of the sample apps. In supervised learning pre-labelled data is used to train the system. The annotated data is read by the system then memorized and then that data is used to distinguish alike malware), wherein:
“each of the first programs is expressed in a first language” (see Koli page 3, 8-11, Phase I is the process of reverse engineering where, the apps apk files were decompiled into their source code in the forms of AndroidManifest.xml and java classes by using Androguard malware analysis tool [10]);
“the machine learning model is generated through training with use of training data including first feature vectors and identification information items, each of the first feature vectors being obtained by extracting a feature of a different one of the first programs, each of the identification information items indicating whether a corresponding one of the first programs is malicious” (see Koli, page 4, lines 12- 21, In training phase, a set of features are parsed and extracted from the source code of a training set sample of malware and Goodware apps; The extracted features are then represented in binary vector format; next the set of binary vector of apps along with label information is passed into learning module where various machine learning algorithms are trained with the data set to build classification model.); and
“each of the first feature vectors is expressed in a first format indicating whether each of first functions of a program expressed in the first language is to be used by the corresponding one of the first programs” (see Koli page 3, line 34-page 4, line 2, If a particular api call/permission/presence of key feature is present in the application, then the corresponding features xi is defined as 1 otherwise as 0);
“outputs an identification result indicating whether the second program is malicious, the identification result being obtained by inputting, to the machine learning model, the second feature vector whose format has been converted into the first format” (see Koli, page 4, lines 21- 27, In the prediction phase, the same set of features are extracted from source code and binary vector is generated for testing set sample of goodware and malware. Then generated binary vector is passed into classifier module where classification happens with the help of classification models built in the training phase. The result is available in the form of predicted label as Goodware or Malware);
Koli does not explicitly discloses generates a second feature vector by extracting a feature of a second program expressed in a second language different from the first language;
wherein the second feature vector is expressed in a second format indicating whether each of second functions of a program expressed in the second language is to be used by the second program; converts a format of the second feature vector generated into the first format.
However, in analogues art, Lee discloses generates a second feature vector by extracting a feature of a second program expressed in a second language different from the first language (see Lee par. 0013, generating, at a processor, a feature vector of a source sentence, wherein the source sentence may be written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a target sentence, wherein the target sentence may be written in a second language; and generating, at the processor, a normalized sentence from the feature vector of the target sentence by transforming the target sentence); wherein the second feature vector is expressed in a second format indicating whether each of second functions of a program expressed in the second language is to be used by the second program (see Lee par. 0102, the decoder decodes the embedding vector of the normalized sentence and generates a target sentence written in a second language. The decoder translates the normalized sentence written in the first language into the target sentence written in the second language); converts a format of the second feature vector generated into the first format (see Lee par. 0106, The decoder decodes the feature vector of the source sentence and generates a target sentence written in a second language. A normalization layer included in the decoder converts the target sentence to a normalized sentence. For example, the normalization layer in the decoder converts a feature vector of the target sentence to a feature vector of the normalized sentence, and the decoder outputs a final target sentence based on the feature vector of the normalized sentence).
Therefore it would have been obvious to a person of ordinary skill in the art before the effective filing date of the application to incorporate the teachings of Lee into the system of Koli to generate, at a processor, a feature vector of a source sentence, wherein the source sentence may be written in a first language; converting, at the processor, the feature vector of the source sentence to a feature vector of a normalized sentence; and generating, at the processor, a target sentence from the feature vector of the normalized sentence, wherein the target sentence corresponds to the source sentence and may be written in a second language (see Lee par. 0006).
Regarding claim 10, a non-transitory computer-readable recording medium for use in a computer, the recording medium having recorded thereon a computer program for causing the computer to execute the program identification method according to claim 1.
(Claim 10 is rejected for the same reason as claim 1)
Allowable Subject Matter
10. Claims 7-8 are objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
Conclusion
11. The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
Wang et al. (US 2021/0174031 A1): discloses The present disclosure describes methods, devices, and storage medium for generating a natural language description for a media object. The method includes respectively processing, by a device, a media object by using a plurality of natural language description models to obtain a plurality of first feature vectors corresponding to a plurality of feature types. The device includes a memory storing instructions and a processor in communication with the memory. The method also includes fusing, by the device, the plurality of first feature to obtain a second feature vector; and generating, by the device, a natural language description for the media object according to the second feature vector, the natural language description being used for expressing the media object in natural language. The present disclosure resolves the technical problem that natural language description generated for a media object can only give an insufficiently accurate description of the media object.
Grebennikov et al. (US 2022/0210169 A1): discloses systems and method for optimizing artificial intelligence (A.I)-based malware analysis on offline endpoints in a network. In one aspect, a method includes identifying a file that has not been executed on an endpoint system and scanning the endpoint system to detect malicious behavior using a machine learning algorithm. In response to determining that the endpoint system does not exhibit malicious behavior based on the machine learning algorithm, the method includes enabling execution of the file. Subsequent to the execution of the file, the method includes rescanning the endpoint system to detect malicious behavior using the machine learning algorithm. In response to determining that the endpoint system does exhibit malicious behavior subsequent to the execution, the method includes extracting attributes of the file and retraining the machine learning algorithm using the extracted attributes to detect malicious behavior associated with the file without having to execute the file.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to SAMUEL AMBAYE whose telephone number is (571)270-7635. The examiner can normally be reached M-F 9:00 AM - 6:00 PM.
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, Jeffrey Pwu can be reached at (571) 272-6798. 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.
/SAMUEL AMBAYE/Examiner, Art Unit 2433
/JEFFREY C PWU/Supervisory Patent Examiner, Art Unit 2433
Prosecution Insights