Prosecution Insights
Last updated: November 04, 2026
Application No. 19/073,787

METHOD AND SYSTEM FOR DETECTING SOCIAL ENGINEERING ATTACKS

Final Rejection §103§112
Filed
Mar 07, 2025
Examiner
GEE, JASON KAI YIN
Art Unit
2495
Tech Center
2400 — Computer Networks
Assignee
Protego LLC
OA Round
2 (Final)
78%
Grant Probability
Favorable
3-4
OA Rounds
1y 4m
Est. Remaining
99%
With Interview

Examiner Intelligence

Grants 78% — above average
78%
Career Allowance Rate
606 granted / 781 resolved
+19.6% vs TC avg
Strong +24% interview lift
Without
With
+23.7%
Interview Lift
resolved cases with interview
Typical timeline
3y 0m
Avg Prosecution
19 currently pending
Career history
808
Total Applications
across all art units

Statute-Specific Performance

§101
11.0%
-29.0% vs TC avg
§103
50.7%
+10.7% vs TC avg
§102
9.6%
-30.4% vs TC avg
§112
21.4%
-18.6% vs TC avg
Black line = Tech Center average estimate • Based on career data from 781 resolved cases

Office Action

§103 §112
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 . This action is response to communication: response to amendments/arguments filed on 09/03/2026 Claims 1-21 are currently pending in this application. Claim 21 is new. No IDS has been filed for this application. Response to Arguments The prior 112 rejections have been withdrawn in response to applicant’s amendments. Applicant’s arguments concerning the 103 rejections have been fully considered but are moot in view of new grounds of rejection. See amended rejection below. Claim Rejections - 35 USC § 112 The prior 112 rejections have been withdrawn in response to applicant’s amendments. 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. Claim(s) 1-6, 8, 11, 13, 15, 16, and 18-21 are rejected under 35 U.S.C. 103 as being unpatentable over Mushtaq US Patent No. 11,595,437 (Mushtaq), in view of Chowdhury et al. US Patent Application Publication 2025/0086656 (Chowdhury), and further in view of Mushtaq US Patent 12,580,958 (Mushtaq B) As per claim 1, Mushtaq teaches a method for detecting social engineering attacks, comprising: extracting, using one or more system interaction interfaces, content presented in a communication interface of an application running on a display screen of an electronic device (col. 3 lines 49-60 with endpoint agent deployed on endpoint device with endpoint agent built into an application; system configured to detect phishing on that application and device; also see col. 6 lines 35-45; see further col. 20 line 37-45/ further see col. 18 lines 13-30 with extracting information from display); analysing the extracted content to identify communication risk factors and generating a structured query based on the analysis (col. 18 lines 12-55 with extracting information and sending to an machine learning engine; for example, agent may extract sender’s information , message body and link within message to extract machine learning features that can be fed into local machine learning to detect presence of phishing text ); feeding the structured query to an on-premise AI model that assesses a likelihood of a potential social engineering attack and generates an output indicating that the potential social engineering attack is associated with the extracted content presented on the application (col. 18 lines 12-55; system may send warning alerts; also see col. 19 lines 20-25; see further col. 20 line 35-45; see col. 18 lines 13-31 with analyzing extracted on a screen); receiving, from the on-premise AI model, the output indicating that the potential social engineering attack is associated with the extracted content presented in the application (col. 18 lines 12-155 with warning alerts; also see col. 19 lines 20-25; see further col. 20 line 35-45); and generating an intervention prompt based on the output from the on-premise AI model within the application(col. 20 lines 38-50 with generating and sending warnings). Although Mushtaq teaches generating intervention prompts, Mushtaq does not explicitly teach wherein the intervention prompt is configured to facilitate verification of the sender’s authenticity within the application. However, facilitating verification of a sender’s authenticity within the application would have been obvious. For example, see Chowdhury (paragraph 30, with mitigation strategies including checking identity of caller). At the time the invention was filed it would have been obvious to one of ordinary skill in the art to combine the teachings of Mushtaq with Chowdhury. One of ordinary skill in the art would have been motivated to perform such an addition to increase security by prevening social engineering scams (paragarphs 2-3 of Chowdhury). Although the Mushtaq combination teaches extracting data form user interfaces, the combination does not explicitly teach the communication interface presenting at least a portion of a conversation between at least two parties, the extracted content comprising one or more messages exchanged between the at least two parties and information identifying which of the at least two parties is assocaited with each of the one or more messages. This would have been obvious though. For example, see Mushtaq B (col. 4 lines 45-62 with identifying and analyzing chat/SMS to identify attack; system may identify user;)/ At the time the invention was filed, it would have been obvious to one of ordinary skill in the art to combine the teachings of the Mushtaq combination with Mushtaq B. One of ordinary skill in the art would have been motivated to perform such an addition to create more security by identifying sophisticated and evolving attacks (col. 1 lines 24-36). As per claim 2, the Mushtaq combination teaches wherein the communication risk factors comprise at least one of linguistic patterns, contextual attributes, sender-related infroamtion, behavioral anomalies, psychological manipulation indicators, or message structure characteristics (Mushtaq col. 18 lines 40-50 with sender-related information, col. 20 lines 60 to col. 21 line 3 with content, etc ) As per claim 3, it would have been obvious over the Mushtaq combination wherein the sender-related information comprises determining whether a sender of the extracted content is in a predefined contact list assocaited with the application(col. 16 lines utilizing blacklist and comparing SMS; see also col. 9 lines 35-45 with analyzing sender’s phone number and utilizing blacklist), the behaviorial anomalies comprise detecting unusual message patterns indicative of social engineering, including urgency, financial requests, or impersonation attempts (col. 21 liens 1-3 with financial request; also see Chowdhury paragraph 31), the linguistic patterns comprise classifying entities within the extracted content to identify persons, organizations, or government agencies (col. 18 lines 11-30 with using natural language processing to determine social engineering; may further extract sender’s information; see also Chowdhury paragraph 31), and the contextual attributes comprise assess prior interactions with the snder to detect anomalies in conversation patterns (paragraph 31 of Chowdhury). As per claim 4, the Mushtaq combination teaches wherein extracting the content comprises image-based text from the application (col. 18 lines 12-31 with OCR; also see col. 7 lines 1-15). As per claim 5, the Mushtaq combination teaches wherein capturing image-based text includes using OCR to extract textual information from screenshots or chat interfaces (obvious to one of ordinary skill in the art to utilize OCR to extract information; also see Mushtaq col. 7 lines 1-15;). As per claim 6, the Mushtaq combination teaches wherein the on-premise AI model assigns a confidence score to the likelihood of the social engineering attack (Chowdhury paragraph 51 with risk score). As per claim 8, the Mushtaq combination teaches wherein generating the intervention prompt includes presenting a message that encourages scepticism towards a sender of the extracted content (col. 20 lines 38-50 with generating and sending warnings). As per claim 11, it would have been obvious over the Mushtaq combination wherein generating the intervention prompt includes displaying official cybersecurity advisories or government notices relevant to the potential social engineering attack (obvious over Mushtaq; see col. 21 line 15-38 with educational warning page). As per claim 13, it would have been obvious voer the Mushtaq combination wherein generating the intervention prompt includes highlighting suspicious linguistic patterns, such as urgency-based language or financial requests, within the extracted content (obvious over the Mushtaq combination; see col. 27 lines 54-60 with warning alert with screenshot; see also Figure 29). As per claim 15, the Mushtaq combination teaches further comprising filtering the extracted content upon determining, based on the output form the on-premise AI model, that the extracted content is associated with the potential social engineering attack (abstract and throughout with blocking content if it is determined that it is a phishing attack). As per claim 16, the Mushtaq combination teaches wherein filtering comprises blocking, delaying, or restricting interactions based on the likelihood of the potential social engineering attack (Mushtaq abstract and throughout with blocking interaction). As per claim 18, it would have been obvious over the Mushtaq combination to further comprise integrating the application with the on-premise AI model using APIs supplied by the on premise AI model for communication and processing, wherein the integration is performed using an AI model library (obvious over Mushtaq combination; see col. 8 lines 25-45 and col. 20 lines 50-60 with utilizing API and the machine learning models; see also col. 9 lines 30-40 with installed ai models and also col. 12 lines 15-45; obvious to one of ordinary skill in the art to supply the necessary API utilizing the AI models that are present on on-premise AI model). Claim 19 is rejected using the same basis of arguments used to rejection claim 1 above. Claim 20 is rejected using the same basis of arguments used to reject claim 1 above. As per claim 21, it would have been obvious over the Mushtaq combination wherein extracting the content comprises obtaining the content, via the one or more system interaction interfaces, from text displayed by the communication interface of the application on the display screen of the electronic device (Mushtaq B col. 4 liens 45-60 with using natural language processing to process message in a chat to determine phishing). Claim(s) 7, 9, 10, and 14 are rejected under 35 U.S.C. 103 as being unpatentable over the Mushtaq combination as applied above, and further in view of Jakobsson et al. US Patent Application Publication 2022/0014543 (Jakobsson). As per claim 7, the Mushtaq combination does not explicitly teach wherein generating the intervention prompt includes suggesting one or more verification questions based on the confidence score from the on-premise AI model. However, generating intervention prompts including suggesting one or more verification questions based on the confidence score is well known in the art. For example, see Jakobsson (paragraph 63 with based on risk assessment, different actions are utilized, including challenge-resposne mechanisms sent to sender) At the time the invention was filed, it would have been obvious to one of ordinary skill in the art to combine the teachings of the Mushtaq combination with Jakobsson. One of ordinary skill in the art would have been motivated to perform such an addition to increase security by determining a measure of confidence that a sender is the actual sender (paragraph 34). As per claim 9, the Mushtaq combination does not explicitly teach wherein generating the intervention prompt includes displaying an authentication challenge to verify a sender of the extracted content. However, this would have been obvious. For example, see Jakobsson (paragraph 118 and throughout). At the time the invention was filed, it would have been obvious to one of ordinary skill in the art to combine the teachings of the Mushtaq combination with Jakobsson. One of ordinary skill in the art would have been motivated to perform such an addition to increase security by determining a measure of confidence that a sender is the actual sender (paragraph 34). As per claim 10, the Mushtaq combination does not explicitly teach wherein generating the intervention prompt includes suggesting one or more verification questions based on prior interactions associated with a sender of the extracted content. However, this would have been obvious. For example, see Jakobsson (paragraph 274). At the time the invention was filed, it would have been obvious to one of ordinary skill in the art to combine the teachings of the Mushtaq combination with Jakobsson. One of ordinary skill in the art would have been motivated to perform such an addition to increase security by determining a measure of confidence that a sender is the actual sender (paragraph 34). As per claim 14, the Mushtaq combination teaches wherein the verification questions are selected based on context of a message in the extracted content, including whether the sender is impersonating a known contact or a financial instutition (obvious over Jakobsson; see paragraph 247 with different challenges and may be based on impersonation of known contact) Claim(s) 12 is rejected under 35 U.S.C. 103 as being unpatentable over the Mushtaq combination as applied above, and further in view of Elworthy US Patent Application Publication 2018/0359280 (Elworthy). As per claim 12, the Mushtaq combination does not explicitly teach wherein generating the intervention prompt includes displaying a risk score indicating the likelihood of the extracted content being assocaited with the potential social engineering attack. However, displaying a risk score to a user is well known in the art. For example, see Elworthy (paragraph 6). At the time the invention was filed, it would have been obvious to one of ordinary skill in the art to combine the teachings of the Mushtaq combination with Elworthy. One of ordinary skill in the art would have been motivated to perform such an addition to increase security by providing an end user with visibility and insight into risk factors (paragraph 6 of Elworthy). Claim(s) 17 is rejected under 35 U.S.C. 103 as being unpatentable over the Mushtaq combination as applied above, and further in view of Malleshiaiah et al. US Patent Application Publication 2025/0377967 (Malleshiaiah) As per claim 17, the Mushtaq combination does not explicitly teach wherein feeding the structured query to the on-premise AI model includes utilizing RAG to enhance detection accuracy by retrieving relevant threat intelligence data and incorporating int onto the on premise AI model’s response. However, utilizing RAG with AI to generate responses is well known in the art. For example, see Malleshiaiah paragraphs 87, 99, and 100. At the time the invention was filed, it would have been obvious to one of ordinary skill in the art to combine the teachings of Malleshiaiah with the Mushtaq combination. One of ordinary skill in the art would have been motivated to perform such an addition to retrieve information and to utlize it to generate coherent and contextually appropriate responses (paragraph 87 of Malleshiaiah). 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 JASON KAI YIN GEE whose telephone number is (571)272-6431. The examiner can normally be reached on Monda-Friday 8:30-5:00 PST Pacific. If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Farid Homayounmehr can be reached on (571) 272-3739. 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 the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). /JASON K GEE/Primary Examiner, Art Unit 2495
Read full office action

Prosecution Timeline

Mar 07, 2025
Application Filed
Jun 10, 2026
Non-Final Rejection mailed — §103, §112
Sep 03, 2026
Response Filed
Sep 24, 2026
Final Rejection mailed — §103, §112 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12775686
Smart Device Management Resource Picker
3y 5m to grant Granted Oct 27, 2026
Patent 12775947
Authentication Question Topic Exclusion Based on Response Hesitation
2y 4m to grant Granted Oct 27, 2026
Patent 12748885
SYSTEM AND METHOD FOR CONTROLLING ACCESS TO ACCOUNT TRANSACTION INFORMATION
2y 8m to grant Granted Sep 29, 2026
Patent 12743546
SYSTEMS AND METHODS FOR PROTECTING DATA USING A PERSONAL DATA STORE CONTROLLED BY THE DATA SUBJECT
2y 10m to grant Granted Sep 22, 2026
Patent 12730928
CONTROLLING A SCREENSHOT FUNCTION TO OBFUSCATE SENSITIVE INFORMATION IN A SCREENSHOT
2y 4m to grant Granted Sep 08, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

Strategy Recommendation AI-generated — please review before filing

Get a prosecution strategy drawn from examiner precedents, rejection analysis, and claim mapping.
Typically takes 5-10 seconds — AI-generated, attorney review required before filing

Prosecution Projections

3-4
Expected OA Rounds
78%
Grant Probability
99%
With Interview (+23.7%)
3y 0m (~1y 4m remaining)
Median Time to Grant
Moderate
PTA Risk
Based on 781 resolved cases by this examiner. Grant probability derived from career allowance rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month