ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments | Paper Citation Record

Observation 359dff9b-95ee-46fb-a4ca-ad762f087302 · outbound

This paper cites VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments VulWeaver: Weaving Broken Semantics for Grounded Vulnerability Detection

Reference 1

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:35.999600Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e0a517e5-b97b-47e0-bda5-95ccd61b4517 · outbound

This paper cites A theory of dual channel constraints.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments A theory of dual channel constraints

Reference 2

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.004027Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 03d3aa39-c6a5-4dae-804c-f21145889107 · outbound

This paper cites naturalizing.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments naturalizing

Reference 3

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.007347Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ae88985-18cb-42be-8252-f38ccdab8c23 · outbound

This paper cites Securing AI Agents with Information-Flow Control.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Securing AI Agents with Information-Flow Control

Reference 4

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.011136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 09d8014f-0318-4c36-b413-639976e3954f · outbound

This paper cites Abstract interpreta- tion: A unified lattice model for static analysis of pro- grams by construction or approximation of fixpoints.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Abstract interpreta- tion: A unified lattice model for static analysis of pro- grams by construction or approximation of fixpoints

Reference 5

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.014686Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e3826c43-d958-4266-85c9-4faa1a5f6328 · outbound

This paper cites Defeating Prompt Injections by Design.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Defeating Prompt Injections by Design

Reference 6

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.017835Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 214363f3-47ce-42f8-957e-f57c4db13a5f · outbound

This paper cites Re- ducing false positives in static bug detection with llms: An empirical study in industry.arXiv preprint arXiv:2601.18844, 2026.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Re- ducing false positives in static bug detection with llms: An empirical study in industry.arXiv preprint arXiv:2601.18844, 2026

Reference 7

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.021370Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 201b0d23-30c6-45c7-b320-3d3768794dfd · outbound

This paper cites Minimizing False Positives in Static Bug Detection via LLM-Enhanced Path Feasibility Analysis.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Minimizing False Positives in Static Bug Detection via LLM-Enhanced Path Feasibility Analysis

Reference 8

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.024104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cb97a8b-17c7-4c91-8601-230598814cdb · outbound

This paper cites Vul-rag: Enhancing llm-based vulnerability detection via knowledge-level rag.ACM Transactions on Software Engineering and Methodol- ogy, 2024.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Vul-rag: Enhancing llm-based vulnerability detection via knowledge-level rag.ACM Transactions on Software Engineering and Methodol- ogy, 2024

Reference 9

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.027753Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ab954a04-2883-4864-84d9-514ff1503aaf · outbound

This paper cites Syceval: Evaluating llm 14 sycophancy.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Syceval: Evaluating llm 14 sycophancy

Reference 10

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.030645Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dea991a1-45b5-4190-b34a-d01230f7915e · outbound

This paper cites PISanitizer: Preventing prompt injec- tion to long-context LLMs via prompt sanitization, 2025.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments PISanitizer: Preventing prompt injec- tion to long-context LLMs via prompt sanitization, 2025

Reference 11

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.033519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 735a8b0d-061d-4241-8dbb-3cca64887624 · outbound

This paper cites an unresolved cited work.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Unresolved cited work

Reference 12

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.036798Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6ce69f66-e586-4ef4-a318-8f4460c4d08e · outbound

This paper cites Incremental analysis for code scanning.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Incremental analysis for code scanning

Reference 13

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.039417Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 396f1db1-d829-41d2-befe-d87a6bcf666a · outbound

This paper cites Ai-powered security detections.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Ai-powered security detections

Reference 14

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.042245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 651287d8-3863-4d56-ad98-534983148dea · outbound

This paper cites Prompt injection attacks in large language models and AI agent systems: A com- prehensive review of vulnerabilities, attack vectors, and defense mechanisms.Information, 17(1), 2026.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Prompt injection attacks in large language models and AI agent systems: A com- prehensive review of vulnerabilities, attack vectors, and defense mechanisms.Information, 17(1), 2026

Reference 15

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.044852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efc6688f-d112-440f-ab4b-bcf6ef614ea0 · outbound

This paper cites RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments RepoAudit: An Autonomous LLM-Agent for Repository-Level Code Auditing

Reference 16

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.048659Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b434ee78-de1c-4bea-b4e8-0d0fce1979c6 · outbound

This paper cites Defending Against Indirect Prompt Injection Attacks With Spotlighting.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Defending Against Indirect Prompt Injection Attacks With Spotlighting

Reference 17

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.051904Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 67d57877-6a3f-4052-be0b-2cd911be265b · outbound

This paper cites An empirical study of suppressed static anal- ysis warnings.Proceedings of the ACM on Software Engineering, 2(FSE):290–311, 2025.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments An empirical study of suppressed static anal- ysis warnings.Proceedings of the ACM on Software Engineering, 2(FSE):290–311, 2025

Reference 18

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.055183Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 92778ed3-17af-4d76-bb3c-04c684d818cf · outbound

This paper cites an unresolved cited work.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Unresolved cited work

Reference 19

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.058340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a37546c9-3c3e-406f-84d5-54e12f1ae1d2 · outbound

This paper cites an unresolved cited work.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Unresolved cited work

Reference 20

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.061052Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 802e0e00-39d2-48d7-a13f-1e3c8ce69249 · outbound

This paper cites an unresolved cited work.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Unresolved cited work

Reference 21

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.063783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a2844616-ae78-4d21-b845-b8a878bf8d3d · outbound

This paper cites Llm-based vulnerability detection at project scale: An empirical study.arXiv preprint arXiv:2601.19239, 2026.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Llm-based vulnerability detection at project scale: An empirical study.arXiv preprint arXiv:2601.19239, 2026

Reference 22

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.066764Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f401c4b3-2c38-4d41-a8fc-3024b507fa23 · outbound

This paper cites Cotdeceptor: Adversarial code obfuscation against cot-enhanced llm code agents.arXiv preprint arXiv:2512.21250, 2025.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Cotdeceptor: Adversarial code obfuscation against cot-enhanced llm code agents.arXiv preprint arXiv:2512.21250, 2025

Reference 23

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.069667Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 536d8f07-8621-4cd0-9e03-8959e3e3446c · outbound

This paper cites Make a feint to the east while attacking in the west: Blinding llm- based code auditors with flashboom attacks.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Make a feint to the east while attacking in the west: Blinding llm- based code auditors with flashboom attacks

Reference 24

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.072633Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a99272f-503c-4dd8-bcfd-d5e3ab46a08d · outbound

This paper cites Make a feint to the east while attacking in the west: Blinding LLM-based code auditors with Flashboom attacks.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Make a feint to the east while attacking in the west: Blinding LLM-based code auditors with Flashboom attacks

Reference 25

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.075426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9618858c-1c7c-4604-9d7d-89eb076938e1 · outbound

This paper cites From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments From SFT to RL: Demystifying the Post-Training Pipeline for LLM-based Vulnerability Detection

Reference 26

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.078626Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f99f694f-211b-49b3-8682-2c1552469a67 · outbound

This paper cites Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Everything You Wanted to Know About LLM-based Vulnerability Detection But Were Afraid to Ask

Reference 27

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.081906Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9746730b-718b-4191-bc73-4a8518f11db9 · outbound

This paper cites IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments IRIS: LLM-Assisted Static Analysis for Detecting Security Vulnerabilities

Reference 28

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.085008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7512d795-92cc-4b62-93ac-09b09473eabb · outbound

This paper cites LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments LLM Can be a Dangerous Persuader: Empirical Study of Persuasion Safety in Large Language Models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.088046Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b5723c4e-5801-45e1-a5a8-8cb33feb84b0 · outbound

This paper cites "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments "Do Not Mention This to the User": Detecting and Understanding Malicious Agent Skills in the Wild

Reference 30

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.091115Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 33d29a78-2ccb-4a65-9ac8-237a7a08b34f · outbound

This paper cites Reasoning hijacking: The fragility of reasoning align- ment in large language models.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Reasoning hijacking: The fragility of reasoning align- ment in large language models

Reference 31

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.095147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00b0752a-c480-47ef-b4ad-e2f4ae1b64fd · outbound

This paper cites Clang static analyzer.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Clang static analyzer

Reference 32

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.098012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2145f295-958a-4803-9326-ccdb49095742 · outbound

This paper cites an unresolved cited work.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Unresolved cited work

Reference 33

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.100770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f8aeef37-713e-40b9-b15b-24295244b9f9 · outbound

This paper cites Prompt injection at- tacks on agentic coding assistants: A systematic analysis of vulnerabilities in skills, tools, and protocol ecosys- tems, 2026.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Prompt injection at- tacks on agentic coding assistants: A systematic analysis of vulnerabilities in skills, tools, and protocol ecosys- tems, 2026

Reference 34

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.103691Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b8622fe9-6bdf-49a6-8d9c-555d99eb7b04 · outbound

This paper cites Cppcheck: A tool for static c/c++ code analysis.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Cppcheck: A tool for static c/c++ code analysis

Reference 35

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.106509Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7eef4a31-a190-4a23-b926-d3e3be22fb4a · outbound

This paper cites Sevra-bench: Social engineering of vulnerabilities in review agents, 2026.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Sevra-bench: Social engineering of vulnerabilities in review agents, 2026

Reference 36

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.109393Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8445e12-8500-4a47-af5e-fe8a88745563 · outbound

This paper cites Infer: A static analyzer for java, c, c++, and objective-c.https://fbinfer.com/, 2024.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Infer: A static analyzer for java, c, c++, and objective-c.https://fbinfer.com/, 2024

Reference 37

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.112248Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb8b29dd-039f-4711-82ca-3f1874de9698 · outbound

This paper cites Microsoft digital defense report 2025: Light- ing the path to a secure future.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Microsoft digital defense report 2025: Light- ing the path to a secure future

Reference 38

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.115043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 832d5c17-9d28-4100-9e49-5fad25af5e3d · outbound

This paper cites Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Measuring and Exploiting Contextual Bias in LLM-Assisted Security Code Review

Reference 39

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.117931Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d91a8940-4142-42ad-b28b-3b0e70466250 · outbound

This paper cites MegaVul: A c/c++ vulnerability dataset with comprehensive code representations.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments MegaVul: A c/c++ vulnerability dataset with comprehensive code representations

Reference 40

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.120804Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 64d94cb1-650b-4912-8438-cdda544a8bec · outbound

This paper cites Lis- tening to programmers—taxonomies and characteristics of comments in operating system code.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Lis- tening to programmers—taxonomies and characteristics of comments in operating system code

Reference 41

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.123579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 26285cb6-55e2-40a9-8013-a353390c8497 · outbound

This paper cites Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems

Reference 42

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.126618Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ec18a865-289c-4452-b7e1-cc8f51e7a2f7 · outbound

This paper cites Secret breach detection in source code with large language models.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Secret breach detection in source code with large language models

Reference 43

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.130106Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a104144a-3cde-4052-b387-507322cce0ca · outbound

This paper cites Backdoors in Neural Models of Source Code.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Backdoors in Neural Models of Source Code

Reference 44

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.133077Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a2c6889-97fd-4882-8727-1066a9d59700 · outbound

This paper cites Agentic Much? Adoption of Coding Agents on GitHub.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Agentic Much? Adoption of Coding Agents on GitHub

Reference 45

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.137025Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c4253d6-323f-4b50-91ab-31792da47150 · outbound

This paper cites You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments You Autocomplete Me: Poisoning Vulnerabilities in Neural Code Completion

Reference 46

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.140068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e5a863df-aa8c-44ec-abf3-1d80df41c0dd · outbound

This paper cites Llms in software security: A survey of vulnerability detection techniques and insights.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Llms in software security: A survey of vulnerability detection techniques and insights

Reference 47

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.143155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7b11ff17-97f5-4b3c-96e9-8b98b1c76a17 · outbound

This paper cites Promptarmor: Simple yet effective prompt injection defenses, 2025.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Promptarmor: Simple yet effective prompt injection defenses, 2025

Reference 48

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.145938Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 31f71e45-b11a-46c3-91b0-6473dd525f99 · outbound

This paper cites Pull request analy- sis.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Pull request analy- sis

Reference 49

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.148684Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4020683f-28bf-4d2d-b8ef-373e4e8e88d8 · outbound

This paper cites Syntax- and compilation-preserving evasion of llm vulnerability de- tectors, 2026.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Syntax- and compilation-preserving evasion of llm vulnerability de- tectors, 2026

Reference 50

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.151568Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a6b624c-f424-4a95-a7c9-6862f478eb24 · outbound

This paper cites Coverity static analysis.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Coverity static analysis

Reference 51

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.154589Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2ac79f46-34cb-4802-a496-96f327999120 · outbound

This paper cites Tomassi and Cindy Rubio-González.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Tomassi and Cindy Rubio-González

Reference 52

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.161367Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 46013548-4a26-449b-b84a-afcb2451075a · outbound

This paper cites VulnLLM-R: A fine-tuned reasoning model for vulnerability detection.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments VulnLLM-R: A fine-tuned reasoning model for vulnerability detection

Reference 53

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.165139Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c50c3205-cad9-437f-90d1-51cd9968a3f8 · outbound

This paper cites Measuring LLM Trust Allocation Across Conflicting Software Artifacts.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Measuring LLM Trust Allocation Across Conflicting Software Artifacts

Reference 54

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.168169Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ccff77c9-e108-46c9-996d-3781a5a13cac · outbound

This paper cites The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments The Instruction Hierarchy: Training LLMs to Prioritize Privileged Instructions

Reference 55

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.171263Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6a86c6aa-24c2-4212-b061-823682aa414f · outbound

This paper cites LLMDFA: Analyzing Dataflow in Code with Large Language Models.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments LLMDFA: Analyzing Dataflow in Code with Large Language Models

Reference 56

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.175377Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f327ff41-5f2c-4446-b0fc-c9c3b778f7b5 · outbound

This paper cites Defending against prompt injection with DataFilter, 2025.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Defending against prompt injection with DataFilter, 2025

Reference 57

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.178694Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a3e70435-c2e9-4c0a-b0bc-7b10fe7d152a · outbound

This paper cites Scale: Constructing struc- tured natural language comment trees for software vul- nerability detection.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Scale: Constructing struc- tured natural language comment trees for software vul- nerability detection

Reference 58

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.182424Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 768facd7-4344-4843-9ccf-e31c596d0599 · outbound

This paper cites Let the trial begin: A mock-court approach to vulnerabil- ity detection using llm-based agents.arXiv preprint arXiv:2505.10961, 2025.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Let the trial begin: A mock-court approach to vulnerabil- ity detection using llm-based agents.arXiv preprint arXiv:2505.10961, 2025

Reference 59

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.186005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation faeededd-4102-4dd3-8547-125c1b169ddd · outbound

This paper cites Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering

Reference 60

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.188774Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d55535f-c6ea-49e3-9262-4e0740dc7918 · outbound

This paper cites Natural Attack for Pre-trained Models of Code.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Natural Attack for Pre-trained Models of Code

Reference 61

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.192043Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c508a3db-130b-452a-958d-286fec2ad66b · outbound

This paper cites Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Adaptive Attacks Break Defenses Against Indirect Prompt Injection Attacks on LLM Agents

Reference 62

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.195909Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 407e8365-0369-4d4f-9c67-328640f82f9d · outbound

This paper cites Vultrlm: Llm-assisted vulnerability detec- tion via ast decomposition and comment enhancement.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Vultrlm: Llm-assisted vulnerability detec- tion via ast decomposition and comment enhancement

Reference 63

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.199519Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 80af0448-6603-4854-b9a3-e780f1b73a96 · outbound

This paper cites Analyze the function step by step... Do not assume vulnerabilities — only report what is supported by the code and context.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Analyze the function step by step... Do not assume vulnerabilities — only report what is supported by the code and context

Reference 64

Resolution: unresolved; no resolver link, observed 2026-07-31T04:54:36.203173Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e21ed7a7-3bae-4524-baaf-6a5647b42a50 · outbound

This paper cites an unresolved cited work.

ALIBI: Adaptive Agentic Attacks on LLM-Based Vulnerability Detectors via Adversarial Code Comments Unresolved cited work

Reference 2026

Resolution: parse uncertain; no resolver link, observed 2026-07-31T04:54:36.158419Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers