Prosecution Insights
Last updated: April 19, 2026
Application No. 18/903,354

ZERO-SHOT BLACK-BOX DETECTION OF NEURAL TROJANS

Non-Final OA §101§102
Filed
Oct 01, 2024
Examiner
HOFFMAN, BRANDON S
Art Unit
2433
Tech Center
2400 — Computer Networks
Assignee
Qatar Foundation For Education Science And Community Development
OA Round
1 (Non-Final)
91%
Grant Probability
Favorable
1-2
OA Rounds
2y 9m
To Grant
97%
With Interview

Examiner Intelligence

Grants 91% — above average
91%
Career Allow Rate
1125 granted / 1238 resolved
+32.9% vs TC avg
Moderate +6% lift
Without
With
+6.3%
Interview Lift
resolved cases with interview
Typical timeline
2y 9m
Avg Prosecution
31 currently pending
Career history
1269
Total Applications
across all art units

Statute-Specific Performance

§101
7.7%
-32.3% vs TC avg
§103
34.7%
-5.3% vs TC avg
§102
33.8%
-6.2% vs TC avg
§112
5.2%
-34.8% vs TC avg
Black line = Tech Center average estimate • Based on career data from 1238 resolved cases

Office Action

§101 §102
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 Claims 1-5 are pending in this office action. Information Disclosure Statement The information disclosure statement (IDS) submitted on October 1, 2024, is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner. 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 1-5 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without an "inventive concept" sufficient to transform the abstract idea into a patent-eligible application. The claims are directed to a mathematical algorithm and a process of organizing or analyzing information, which are recognized abstract ideas. Claims 2 and 5 are explicitly directed to a mathematical formula for "Simulated Annealing" and the calculation of "cASR" (continuous Attack Success Rate). The core of the invention involves generating a random trigger, iteratively modifying it, and comparing "old" vs. "new" success rates (scores) to reach a conclusion. This represents a series of mathematical steps for data analysis that can be performed by a human or a computer. The method characterizes the behavior of an external model (the "black-box") solely by analyzing input/output relationships. Identifying patterns in data (Trojan triggers) through iterative optimization is a fundamental mental or mathematical exercise. Step 2A. The claims do not integrate the abstract idea into a practical application that provides a "technical improvement" to a computer or another technology. The system in Claim 1 utilizes a generic "server," "processor," and "memory". These components perform their standard, well-understood functions of storing and executing instructions. While the specification argues that this method is "architecture agnostic" and "data-efficient", the claims do not recite a specific improvement to the functioning of the computer itself. Instead, the computer is merely a tool used to perform the mathematical optimization (simulated annealing) faster than a human could. Step 2B. The claims lack an "inventive concept" that is "significantly more" than the abstract idea itself. Simulated annealing, iterative optimization, and calculating success rates are well-known mathematical techniques in the field of computer science. Limiting the mathematical algorithm to the specific field of "neural Trojan detection" is a "field of use" restriction, which the courts have held does not transform an abstract idea into eligible subject matter. The claims do not detail how the "black-box" model is interacted with in a way that is unique to the hardware; they only describe the logical flow of the algorithm. Because the claims recite a mathematical algorithm (simulated annealing) executed on generic computer hardware to analyze data (cASR), they are directed to an abstract idea and are ineligible for patent protection under 35 U.S.C. 101. Claim Rejections - 35 USC § 102 The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action: A person shall be entitled to a patent unless – (a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention. Claims 1-5 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Feng et al. (Detecting Backdoors in Pre-trained Encoders, 2023). Regarding claim 1, Feng et al. teaches a system for zero-shot black-box detection of neural Trojans comprising: a server (abstract); a processor (abstract); memory storing instructions, which when executed by the processor, cause the processor to apply a zero-shot black-box detection of neural Trojans algorithm (section 1, page 2, “the first backdoor detection approach for pre-trained encoders”). Regarding claim 2, Feng et al. teaches wherein the zero-shot black-box detection of neural Trojans uses an algorithm (section 4.2, pages 4 and 5, “the cosing similarity of these embeddings guides the optimization of trigger”, “minimal trigger size”, “iteratively optimized to the minimal”). Regarding claim 3, Feng et al. teaches a method of using zero-shot black-box detection of neural Trojans comprising: receiving a patch (section 2.1, page 2, “patch like triggers”); performing simulated annealing on the patch using a zero-shot black-box detection of neural Trojans algorithm (section 4.2, page 5, “trigger size is iteratively optimized”); detecting the presence of a Trojan (section 4.2.1, page 5, “detect backdoored encoders” and fig. 3). Regarding claim 4, Feng et al. teaches wherein the patch includes at least one of a random pattern, a size, a shape, or a location (section G.2, page 15, random). Regarding claim 5, Feng et al. teaches wherein the zero-shot black-box detection of neural Trojans uses an algorithm (section 4.2, pages 4 and 5, “the cosing similarity of these embeddings guides the optimization of trigger”, “minimal trigger size”, “iteratively optimized to the minimal”). Any inquiry concerning this communication or earlier communications from the examiner should be directed to BRANDON HOFFMAN whose telephone number is (571)272-3863. The examiner can normally be reached Monday-Friday 8:30AM-5:00PM. 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. /BRANDON HOFFMAN/Primary Examiner, Art Unit 2433
Read full office action

Prosecution Timeline

Oct 01, 2024
Application Filed
Feb 23, 2026
Non-Final Rejection — §101, §102 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12598185
DESCENDENT CASE ROLE ALIAS
2y 5m to grant Granted Apr 07, 2026
Patent 12597311
Access Control System for Electric Vehicle Charging
2y 5m to grant Granted Apr 07, 2026
Patent 12579293
SYSTEMS AND METHODS FOR API GATEWAY SYNCHRONIZATION WITH CLOUD STORAGE
2y 5m to grant Granted Mar 17, 2026
Patent 12579295
SYSTEMS AND METHODS FOR ELECTRONIC DEVICE ACCESS
2y 5m to grant Granted Mar 17, 2026
Patent 12566878
DATA SANITIZER
2y 5m to grant Granted Mar 03, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
91%
Grant Probability
97%
With Interview (+6.3%)
2y 9m
Median Time to Grant
Low
PTA Risk
Based on 1238 resolved cases by this examiner. Grant probability derived from career allow 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