Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response | Paper Citation Record

Observation 4b1ecfb1-a32b-427d-ae04-cc9f047617da · outbound

This paper cites React: Synergizing reasoning and acting in language models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response React: Synergizing reasoning and acting in language models

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:15.784247Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 58f393db-9a36-4052-aa3c-152ea5562d0a · outbound

This paper cites Voyager: An Open-Ended Embodied Agent with Large Language Models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Voyager: An Open-Ended Embodied Agent with Large Language Models

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:15.828479Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cd74131-6803-42da-bbf4-85a8751e8690 · outbound

This paper cites MemGPT: Towards LLMs as Operating Systems.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response MemGPT: Towards LLMs as Operating Systems

Reference 3

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:15.974430Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8818ff40-b6d6-474e-b824-037a810618cc · outbound

This paper cites Security incident disclosure — july 2026.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Security incident disclosure — july 2026

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.055615Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e034f0cd-50c4-4291-8e3d-8f07bf78cab1 · outbound

This paper cites Openai and hugging face partner to address security incident during model evalua- tion.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Openai and hugging face partner to address security incident during model evalua- tion

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.146975Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d4cf60a2-5275-4f63-a535-fe36c38030cd · outbound

This paper cites Investigating three real-world incidents in our cybersecurity evaluations.https:// www.anthropic.com/news/investigating-incidents-cybersecurity-evals, July 2026.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Investigating three real-world incidents in our cybersecurity evaluations.https:// www.anthropic.com/news/investigating-incidents-cybersecurity-evals, July 2026

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.205434Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation af26caf1-267e-4b61-80fd-77ee21c3ec40 · outbound

This paper cites an unresolved cited work.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Unresolved cited work

Reference 7

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.329925Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 230547cb-85cf-4214-b42a-01a3bbc6251d · outbound

This paper cites Ai agents under threat: A survey of key security challenges and future pathways.ACM Computing Surveys, 57(7):1–36, 2025.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Ai agents under threat: A survey of key security challenges and future pathways.ACM Computing Surveys, 57(7):1–36, 2025

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.381013Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23ee8a47-b174-4f68-8a36-446b8781fdf9 · outbound

This paper cites Trustworthy AI: From principles to practices.ACM Computing Surveys, 55(9):177, 2023.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Trustworthy AI: From principles to practices.ACM Computing Surveys, 55(9):177, 2023

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.462334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1901fd3e-b204-464b-a7b5-93bebeaa5abf · outbound

This paper cites Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Agentic AI Security: Threats, Defenses, Evaluation, and Open Challenges

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.528497Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d43477af-b51d-4237-90b5-0ba5b15645b0 · outbound

This paper cites LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response LLM agents security duality: a comprehensive survey of self-security and empowered cybersecurity

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.609232Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac27046b-f2a0-4e2f-959b-56433b82e6dc · outbound

This paper cites Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Not what you’ve signed up for: Compromising real-world llm-integrated applications with indirect prompt injection

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.652342Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d75c3d8c-95af-4c8f-9b15-c9bf185f3dd9 · outbound

This paper cites Prompt Injection attack against LLM-integrated Applications.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Prompt Injection attack against LLM-integrated Applications

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.735859Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b54359a6-bcb2-4682-83a8-d6b0060e1224 · outbound

This paper cites AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response AgentDojo: A dynamic environment to evaluate prompt injection attacks and defenses for LLM agents

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.817208Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0fd2b72-dac0-408c-828b-bb9c482dde02 · outbound

This paper cites ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.909157Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 114118d8-2600-4dc3-b0c5-659119391a12 · outbound

This paper cites Brown, and Francis Rhys Ward.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Brown, and Francis Rhys Ward

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:16.980985Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d52c813-f9d1-4713-9cb1-182b7b01de33 · outbound

This paper cites Alignment faking in large language models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Alignment faking in large language models

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.051827Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d98c3892-abe4-49a7-bdf8-49a72e76b440 · outbound

This paper cites Wong, Xiaowei Huang, Qiufeng Wang, and Kaizhu Huang.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Wong, Xiaowei Huang, Qiufeng Wang, and Kaizhu Huang

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.087617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 44a0fde9-d8e2-4d81-84dc-0884e3032c85 · outbound

This paper cites Models are codes: Towards measuring malicious code poisoningattacksonpre-trainedmodelhubs.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Models are codes: Towards measuring malicious code poisoningattacksonpre-trainedmodelhubs

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.142426Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3146927-b6d0-40a2-8429-c4853861a66d · outbound

This paper cites BackdoorLLM: A compre- hensive benchmark for backdoor attacks and defenses on large language models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response BackdoorLLM: A compre- hensive benchmark for backdoor attacks and defenses on large language models

Reference 20

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.252637Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fec7acb-fbcf-4932-ba50-3a1a319537be · outbound

This paper cites Quantifying Frontier LLM Capabilities for Container Sandbox Escape.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Quantifying Frontier LLM Capabilities for Container Sandbox Escape

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.342231Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5eecdb61-f7a3-4b50-bd63-a7dd32c325c5 · outbound

This paper cites Caging the agents: A zero trust security architecture for autonomous ai in healthcare.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Caging the agents: A zero trust security architecture for autonomous ai in healthcare

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.385588Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ce22be19-6213-4d5a-b898-2220a755b6da · outbound

This paper cites Mythos and the Unverified Cage: Z3-Based Pre-Deployment Verification for Frontier-Model Sandbox Infrastructure.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Mythos and the Unverified Cage: Z3-Based Pre-Deployment Verification for Frontier-Model Sandbox Infrastructure

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.449910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9bd63fa3-065b-47da-b812-7f0fe6789cf9 · outbound

This paper cites Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Catastrophic Cyber Capabilities Benchmark (3CB): Robustly Evaluating LLM Agent Cyber Offense Capabilities

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.528517Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c2eb78e9-4e54-4e10-a6a0-07da0442523b · outbound

This paper cites Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Purple Llama CyberSecEval: A Secure Coding Benchmark for Language Models

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.643282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 01562421-eeb2-4448-82a6-b74dc133ad02 · outbound

This paper cites CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response CyberSecEval 2: A Wide-Ranging Cybersecurity Evaluation Suite for Large Language Models

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.718253Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dc06e131-b236-4097-b755-8ec57ad496b1 · outbound

This paper cites CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.721562Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73831b72-d0ad-4e04-b24b-93457d9a1df9 · outbound

This paper cites Zhang, Neil Perry, Riya Dulepet, Joey Ji, Celeste Menders, Justin W.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Zhang, Neil Perry, Riya Dulepet, Joey Ji, Celeste Menders, Justin W

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.758243Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4799d76c-434d-492c-bd3c-fce70425c30f · outbound

This paper cites Nyu ctf bench: A scalable open-source benchmark dataset for evaluating llms in offensive security.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Nyu ctf bench: A scalable open-source benchmark dataset for evaluating llms in offensive security

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:17.874815Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 62901f7c-247d-46e2-8694-57def320e741 · outbound

This paper cites Training language model agents to find vulnerabilities with ctf-dojo.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Training language model agents to find vulnerabilities with ctf-dojo

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:18.014852Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2b6b1d46-5ba9-4358-a259-7fc5fef82a7f · outbound

This paper cites CTFusion: A CTF-based Benchmark for LLM Agent Evaluation.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response CTFusion: A CTF-based Benchmark for LLM Agent Evaluation

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:18.181697Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 17101f3f-2be3-406d-9b65-ff911fda21f2 · outbound

This paper cites Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Capture the Flags: Family-Based Evaluation of Agentic LLMs via Semantics-Preserving Transformations

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:18.347880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 395d9ebe-03ab-445c-8287-9b655f0b49b4 · outbound

This paper cites CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response CTFExplorer: Evaluating LLM Offensive Agents Through Multi-Target Web CTF Benchmarking

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:18.451383Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c9a45d0d-0a72-454a-b431-6dd3e2cb519e · outbound

This paper cites Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Towards Effective Offensive Security LLM Agents: Hyperparameter Tuning, LLM as a Judge, and a Lightweight CTF Benchmark

Reference 34

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:18.557054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ff05668-26f6-4cfe-9f2e-a6881cf313b2 · outbound

This paper cites an unresolved cited work.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Unresolved cited work

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:18.598260Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 47bd9e88-f30f-44b0-a93c-9a69dddeb1eb · outbound

This paper cites SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response SecBench: A Comprehensive Multi-Dimensional Benchmarking Dataset for LLMs in Cybersecurity

Reference 36

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:18.644653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4fe808f1-b9a6-4eb2-a095-14c19ba9efff · outbound

This paper cites Sec-bench: Automated bench- marking of llm agents on real-world software security tasks.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Sec-bench: Automated bench- marking of llm agents on real-world software security tasks

Reference 37

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:18.806915Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 88bc2482-ae0e-4adf-b530-e8df86e4e0d5 · outbound

This paper cites Do agents dream of root shells? partial-credit evaluation of llm agents in capture the flag challenges.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Do agents dream of root shells? partial-credit evaluation of llm agents in capture the flag challenges

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:18.907167Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fb64236f-b72d-4290-aa0f-e05f363f27c4 · outbound

This paper cites AISI frontier AI trends report (2025).

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response AISI frontier AI trends report (2025)

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.018364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b371816d-fa8c-43b7-ada5-2737a85cb7f4 · outbound

This paper cites Measuring AI Ability to Complete Long Software Tasks.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Measuring AI Ability to Complete Long Software Tasks

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.105611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d31b2288-5544-4e31-9177-925ab32baa41 · outbound

This paper cites Secret cyberspace: The growing risk of AI-enabled cyber operations.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Secret cyberspace: The growing risk of AI-enabled cyber operations

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.196868Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b9235b64-41ab-49e1-9e7c-ee86dc7ff743 · outbound

This paper cites Operationalizing AI-enabled cyberoperations.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Operationalizing AI-enabled cyberoperations

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.265245Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a151a0e6-9652-4d21-86fe-a5def62927a4 · outbound

This paper cites Detecting Offensive Cyber Agents: A Detection-in-Depth Approach.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Detecting Offensive Cyber Agents: A Detection-in-Depth Approach

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.317887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fdeaf38d-8141-458e-9e94-217591ab3591 · outbound

This paper cites Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Injecagent: Benchmarking indirect prompt injections in tool-integrated large language model agents

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.431953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7cc4fbbd-3dbc-41de-8199-ba3b4156b4fd · outbound

This paper cites Memory poisoning attack and defense on memory based llm-agents.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Memory poisoning attack and defense on memory based llm-agents

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.544846Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5906f86f-841a-4efc-a1c3-e66961609351 · outbound

This paper cites The benchmark that broke con- tainment: An openai evaluation model escaped its sandbox and breached hugging face.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response The benchmark that broke con- tainment: An openai evaluation model escaped its sandbox and breached hugging face

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.655825Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20395e23-5f83-4b38-bf09-bab92d33b930 · outbound

This paper cites Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.731256Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9f79381-7679-41b0-9f32-0a6ebc862bab · outbound

This paper cites Optimal policies tend to seek power.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Optimal policies tend to seek power

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.832136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b0062fbb-1487-4717-a5ff-58995bfeb0af · outbound

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

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Supply-Chain Poisoning Attacks Against LLM Coding Agent Skill Ecosystems

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:19.924770Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cc1cd9ce-e7d2-4cfa-8a44-855560a8705e · outbound

This paper cites Model supply chain poisoning: Backdooring pre-trained models via embedding indistinguishability.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Model supply chain poisoning: Backdooring pre-trained models via embedding indistinguishability

Reference 50

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.024421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0e9d7999-2ff2-4d56-b33a-20bf534e2e56 · outbound

This paper cites APT-Agent: Automated Penetration Testing using Large Language Models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response APT-Agent: Automated Penetration Testing using Large Language Models

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.120897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f14c5bb1-18f3-44d9-b604-89e331dbe67c · outbound

This paper cites SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response SysAdmin: Measuring Instrumental Power-Seeking in Frontier AI

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.189768Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 028d3309-188f-49b8-9a21-00d2bf81e06a · outbound

This paper cites Artificial Intelligence as the New Hacker: Developing Agents for Offensive Security.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Artificial Intelligence as the New Hacker: Developing Agents for Offensive Security

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.244999Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dfa9de5f-86aa-4c97-bf44-2ddeaf0d0cbb · outbound

This paper cites Compute trends across three eras of machine learning.https://epoch.ai/publications/ compute-trends, 2024.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Compute trends across three eras of machine learning.https://epoch.ai/publications/ compute-trends, 2024

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.330726Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b2b64cf-abef-4114-9ad0-1c5b1834b20d · outbound

This paper cites When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response When Agents Remember Too Much: Memory Poisoning Attacks on Large Language Model Agents

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.388698Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8de1c133-ebbc-411f-a9b8-957d524402c2 · outbound

This paper cites LLM Agents can Autonomously Hack Websites.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response LLM Agents can Autonomously Hack Websites

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.480890Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 99a44064-1425-488e-baf1-e21b294dc361 · outbound

This paper cites LLM Agents can Autonomously Exploit One-day Vulnerabilities.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response LLM Agents can Autonomously Exploit One-day Vulnerabilities

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.589147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e9239750-4b21-457c-83d3-775a95b46d45 · outbound

This paper cites Teams of LLM Agents can Exploit Zero-Day Vulnerabilities.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.664144Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 66e38e52-c376-4f47-95c6-0e4895419de3 · outbound

This paper cites PentestGPT: An LLM-empowered Automatic Penetration Testing Tool.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response PentestGPT: An LLM-empowered Automatic Penetration Testing Tool

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.742477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5d41388c-3db1-4e58-bb07-d8b86d680402 · outbound

This paper cites HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response HackSynth: LLM Agent and Evaluation Framework for Autonomous Penetration Testing

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.837262Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 77fa3257-b6a1-4c4b-96ae-57bdf59e429c · outbound

This paper cites CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response CVE-Bench: A Benchmark for AI Agents' Ability to Exploit Real-World Web Application Vulnerabilities

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.873642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac68106d-a200-4299-b430-4ecd33b67f01 · outbound

This paper cites Autonomous LLM Agents & CTFs: A Second Look.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Autonomous LLM Agents & CTFs: A Second Look

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:20.956536Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9cc1a18c-1e2c-41c4-b276-72bb55b5e9b8 · outbound

This paper cites Red alarm for pre-trained models: Universal vulnerability to neuron-level backdoor attacks.Machine Intelligence Research, 20(2):180–193, 2023.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Red alarm for pre-trained models: Universal vulnerability to neuron-level backdoor attacks.Machine Intelligence Research, 20(2):180–193, 2023

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.075351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cbc41083-399e-4a16-a41b-ea52a7d7f608 · outbound

This paper cites D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response D-CIPHER: Dynamic Collaborative Intelligent Multi-Agent System with Planner and Heterogeneous Executors for Offensive Security

Reference 64

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.152871Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ccb1427-293a-4aa8-a546-596bf210a9f8 · outbound

This paper cites The Elicitation Game: Evaluating Capability Elicitation Techniques.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response The Elicitation Game: Evaluating Capability Elicitation Techniques

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.186887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bd173fc8-e5a0-4536-b93a-b276c16f0f1f · outbound

This paper cites The Ethics of Autonomous AI Agents for Offensive Security.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response The Ethics of Autonomous AI Agents for Offensive Security

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.238018Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6b100780-976d-4fa9-bd38-5599323fde4a · outbound

This paper cites Detecting sleeper agents in large language models via semantic drift analysis.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Detecting sleeper agents in large language models via semantic drift analysis

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.347700Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 23bf9427-7031-48c6-b773-124b802ec3d5 · outbound

This paper cites Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.407962Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cf133028-860c-446b-a7c8-1e6388544aa3 · outbound

This paper cites Towards understanding sycophancy in language models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Towards understanding sycophancy in language models

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.556074Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 00bbf6b3-a325-4e17-b2fe-ca84d8d26d1b · outbound

This paper cites Sharkey, Jacob Pfau, and David Krueger.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Sharkey, Jacob Pfau, and David Krueger

Reference 70

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.715416Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c3cfefee-288d-4ff4-9887-e636ef2f72c4 · outbound

This paper cites Risks from Learned Optimization in Advanced Machine Learning Systems.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Risks from Learned Optimization in Advanced Machine Learning Systems

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.820084Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 630909b5-2abe-483a-92f6-bb7e82d13312 · outbound

This paper cites Power-seeking can be probable and predictive for trained agents.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Power-seeking can be probable and predictive for trained agents

Reference 72

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:21.933113Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d5cca33b-e34b-4e15-9214-34a7f78f3903 · outbound

This paper cites A Large-Scale Exploit Instrumentation Study of AI/ML Supply Chain Attacks in Hugging Face Models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response A Large-Scale Exploit Instrumentation Study of AI/ML Supply Chain Attacks in Hugging Face Models

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.018563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 0ed56abe-7d94-4aba-8aa7-9dbebbfa0c55 · outbound

This paper cites Safepickle: Robust and generic ml detection of malicious pickle-based ml models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Safepickle: Robust and generic ml detection of malicious pickle-based ml models

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.148720Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 140c0c9b-d1e4-4c7c-9c76-7083d3a73d4a · outbound

This paper cites Kellas, Neophytos Christou, Wenxin Jiang, Penghui Li, Laurent Simon, Yaniv David, Vasileios P.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Kellas, Neophytos Christou, Wenxin Jiang, Penghui Li, Laurent Simon, Yaniv David, Vasileios P

Reference 75

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.266658Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e48605d9-f6ca-4044-a329-935c5173d725 · outbound

This paper cites Defensive refusal bias: How safety alignment fails cyber defenders.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Defensive refusal bias: How safety alignment fails cyber defenders

Reference 76

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.337560Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 68949237-313f-4188-9bcc-61cfe33c18de · outbound

This paper cites Zico Kolter.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Zico Kolter

Reference 77

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.453572Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7c604844-ba65-42fb-a698-1b18614ba36c · outbound

This paper cites Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Can Safety Fine-Tuning Be More Principled? Lessons Learned from Cybersecurity

Reference 78

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.553666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation bc1711a2-3954-4e0d-bf5d-70cbf9104ef4 · outbound

This paper cites Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Ablating Safety: Mechanisms for Removing Alignment in Language Models for Security Applications

Reference 79

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.661751Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d8cbb957-cfe3-4bc0-bdc4-d4da4bd18ae6 · outbound

This paper cites Does Refusal Training in LLMs Generalize to the Past Tense?.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Does Refusal Training in LLMs Generalize to the Past Tense?

Reference 80

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.755140Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5612304a-ed00-4cd8-ba7e-555bb632f2d5 · outbound

This paper cites Mitigating Cyber Risk in the Age of Open-Weight LLMs: Policy Gaps and Technical Realities.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Mitigating Cyber Risk in the Age of Open-Weight LLMs: Policy Gaps and Technical Realities

Reference 81

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.871161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 329b84a3-df99-4980-bf7a-2c45855bccff · outbound

This paper cites Toward Autonomous SOC Operations: End-to-End LLM Framework for Threat Detection, Query Generation, and Resolution in Security Operations.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Toward Autonomous SOC Operations: End-to-End LLM Framework for Threat Detection, Query Generation, and Resolution in Security Operations

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:22.974747Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 460abc09-8e73-473b-b5d1-07f7779152cb · outbound

This paper cites Llms in the soc: An empirical study of human-ai collaboration in security operations centres.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Llms in the soc: An empirical study of human-ai collaboration in security operations centres

Reference 83

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:23.103617Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef46b858-c99f-4c45-a030-a6406fbf9b99 · outbound

This paper cites Cortex: Collaborative llm agents for high-stakes alert triage.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Cortex: Collaborative llm agents for high-stakes alert triage

Reference 84

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:23.250350Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8e6f95e3-c039-4e88-acb4-94423dc28edb · outbound

This paper cites LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response LLM Agent Honeypot: Monitoring AI Hacking Agents in the Wild

Reference 85

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:23.376610Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 16cdcf37-6087-450f-bae1-f742de132164 · outbound

This paper cites Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents

Reference 86

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:23.511579Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cc9fd8e-d5df-408c-add9-3405764624a0 · outbound

This paper cites When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:23.584695Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8f1f32fe-2138-41c1-a2c7-95e9c5a26176 · outbound

This paper cites Audit trails for accountability in large language models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Audit trails for accountability in large language models

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:23.811905Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9d363e54-187e-4cbf-9f5e-b77d655ef997 · outbound

This paper cites When the Agent Is the Adversary: Architectural Requirements for Agentic AI Containment After the April 2026 Frontier Model Escape.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response When the Agent Is the Adversary: Architectural Requirements for Agentic AI Containment After the April 2026 Frontier Model Escape

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:23.914719Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8adfe07-266b-47cd-9b00-ee440303083b · outbound

This paper cites Red teaming language models with language models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Red teaming language models with language models

Reference 90

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:23.981127Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f785cad0-e52a-40c0-8495-3ea4540b3bac · outbound

This paper cites Benchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of AI Foundation Models.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Benchmark Early and Red Team Often: A Framework for Assessing and Managing Dual-Use Hazards of AI Foundation Models

Reference 91

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:24.049880Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 779d00c6-df70-463f-b909-40c2248125ec · outbound

This paper cites Beyond over-refusal: Scenario-based diagnostics and post-hoc mitigation for exaggerated refusals in llms.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Beyond over-refusal: Scenario-based diagnostics and post-hoc mitigation for exaggerated refusals in llms

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:24.200575Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation dd1b7c70-9ec8-4e82-a20e-6edc3519abb7 · outbound

This paper cites Language Models (Mostly) Know What They Know.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Language Models (Mostly) Know What They Know

Reference 93

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:24.370083Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e33ca357-93fa-4709-846a-b568af6dcbb6 · outbound

This paper cites Anthropic responsible scaling policy.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Anthropic responsible scaling policy

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:24.587422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a70ba59-cc93-4470-af08-5ff72ffaa862 · outbound

This paper cites Openai preparedness framework.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Openai preparedness framework

Reference 95

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:24.684332Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f3b815b3-444d-429b-a56d-6058a1f80d04 · outbound

This paper cites EU AI Act, article 15: Accuracy, robustness and cybersecurity.https: //ai-act-service-desk.ec.europa.eu/en/ai-act/article-15, 2024.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response EU AI Act, article 15: Accuracy, robustness and cybersecurity.https: //ai-act-service-desk.ec.europa.eu/en/ai-act/article-15, 2024

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:24.859178Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8daed7da-7dc5-48f5-832f-9c22ea38c934 · outbound

This paper cites Managing advanced cyber risks in frontier AI frameworks.

Cyber-Capable AI Agents: Vulnerabilities, Evaluation Containment, and Defensive Response Managing advanced cyber risks in frontier AI frameworks

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-04T01:33:25.006611Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers