On the Surprising Efficacy of LLMs for Penetration-Testing | Paper Citation Record

Observation f3225ebe-ba01-415d-a6b1-f2e49bf161f7 · outbound

This paper cites Control-flow integrity principles, implementations, and applications.

On the Surprising Efficacy of LLMs for Penetration-Testing Control-flow integrity principles, implementations, and applications

Reference 1

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.314597Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 20e5481e-c1dd-4cb4-8266-d5ec09ef84c6 · outbound

This paper cites O1 is less powerful than o1-preview due to the less time it spends on thinking (compute time).

On the Surprising Efficacy of LLMs for Penetration-Testing O1 is less powerful than o1-preview due to the less time it spends on thinking (compute time)

Reference 2

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.320803Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c52a4c27-1a57-42bc-82d8-84bf99629e55 · outbound

This paper cites Performance of o1 vs.

On the Surprising Efficacy of LLMs for Penetration-Testing Performance of o1 vs

Reference 3

Resolution: verified exact; raw_fallback, observed 2026-08-06T21:10:09.053196Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0bc2b123-44fc-41b7-ad5e-c87f867638bd · outbound

This paper cites Introducing the model context protocol.

On the Surprising Efficacy of LLMs for Penetration-Testing Introducing the model context protocol

Reference 4

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.330529Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4b2a3b2a-8ab9-42ae-b9a1-98df2d552953 · outbound

This paper cites Detecting and countering malicious uses of claude: March.

On the Surprising Efficacy of LLMs for Penetration-Testing Detecting and countering malicious uses of claude: March

Reference 5

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.336114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f02aa17-409e-458c-ba92-f1e86240ef77 · outbound

This paper cites Non-Determinism of "Deterministic" LLM Settings.

On the Surprising Efficacy of LLMs for Penetration-Testing Non-Determinism of "Deterministic" LLM Settings

Reference 6

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.347147Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 79c07c35-0da4-4725-a9c9-b13bbc0ce8b0 · outbound

This paper cites Llms for in- telligent software testing: A comparative study.

On the Surprising Efficacy of LLMs for Penetration-Testing Llms for in- telligent software testing: A comparative study

Reference 7

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T21:10:08.977364Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 3a3130f6-fb7e-4477-8583-3d0b2e9b30f0 · outbound

This paper cites Ai angst.

On the Surprising Efficacy of LLMs for Penetration-Testing Ai angst

Reference 8

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.359510Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation db27d6d7-8b52-4b3f-9cef-cd3d16cb0fb3 · outbound

This paper cites Generative ai at work.

On the Surprising Efficacy of LLMs for Penetration-Testing Generative ai at work

Reference 9

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.363666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a8c7c9e9-7929-42f3-aaa1-8ff06219a2b6 · outbound

This paper cites On large language models in national security applications.

On the Surprising Efficacy of LLMs for Penetration-Testing On large language models in national security applications

Reference 10

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.368448Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8d5ef76a-0a9c-4c1f-b2e5-e2cc2aeb42f7 · outbound

This paper cites Leveling up fuzzing: Finding more vulnerabilities with ai.

On the Surprising Efficacy of LLMs for Penetration-Testing Leveling up fuzzing: Finding more vulnerabilities with ai

Reference 11

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.371574Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3b15cd00-5170-4d33-8115-3ae182f709bb · outbound

This paper cites LlamaFirewall: An open source guardrail system for building secure AI agents.

On the Surprising Efficacy of LLMs for Penetration-Testing LlamaFirewall: An open source guardrail system for building secure AI agents

Reference 12

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.377411Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4eb133aa-2187-46b2-bd27-e30ccb9f55ff · outbound

This paper cites Extracting memorized pieces of (copyrighted) books from open-weight language models.

On the Surprising Efficacy of LLMs for Penetration-Testing Extracting memorized pieces of (copyrighted) books from open-weight language models

Reference 13

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.382357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5ce74feb-3325-4a0e-9b06-7afa0861bf4a · outbound

This paper cites Bias and unfairness in information retrieval systems: New challenges in the llm era.

On the Surprising Efficacy of LLMs for Penetration-Testing Bias and unfairness in information retrieval systems: New challenges in the llm era

Reference 14

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.387221Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 13f48b7b-a5e2-4441-b83d-18379d1ebc07 · outbound

This paper cites Defeating Prompt Injections by Design.

On the Surprising Efficacy of LLMs for Penetration-Testing Defeating Prompt Injections by Design

Reference 15

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.391584Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 30d47ca5-84a4-4b08-bd8a-ac56e8aed790 · outbound

This paper cites {PentestGPT}: Evaluating and harnessing large language models for automated penetration testing.

On the Surprising Efficacy of LLMs for Penetration-Testing {PentestGPT}: Evaluating and harnessing large language models for automated penetration testing

Reference 16

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.396067Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9b660b0f-7c10-41c1-a9ad-a195665dba64 · outbound

This paper cites Schumpeter’s creative destruction: A review of the evidence.

On the Surprising Efficacy of LLMs for Penetration-Testing Schumpeter’s creative destruction: A review of the evidence

Reference 17

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.399421Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2f9e4508-1887-4c13-9e0f-e6ccd1f843c3 · outbound

This paper cites The explainability challenge of generative ai and llms.

On the Surprising Efficacy of LLMs for Penetration-Testing The explainability challenge of generative ai and llms

Reference 18

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.405054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation adaae1a6-4744-4256-ab3f-615205f224de · outbound

This paper cites The potential for jurisdictional challenges to ai or llm training datasets.

On the Surprising Efficacy of LLMs for Penetration-Testing The potential for jurisdictional challenges to ai or llm training datasets

Reference 19

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.415104Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7ad48560-dfdf-49fc-9dd1-92c5c61be25a · outbound

This paper cites Large language models in information security research: A january 2024 survey.

On the Surprising Efficacy of LLMs for Penetration-Testing Large language models in information security research: A january 2024 survey

Reference 20

Resolution: verified exact; raw_fallback, observed 2026-08-06T21:10:08.866942Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 667e80d5-d5e8-4bc9-9437-a1d6061ceb1a · outbound

This paper cites Google’s approach for secure ai agents.

On the Surprising Efficacy of LLMs for Penetration-Testing Google’s approach for secure ai agents

Reference 21

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.423535Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 642e0ffe-f561-4d7d-9dfe-e25d84ae1e4a · outbound

This paper cites Gpts are gpts: Labor market impact potential of llms.

On the Surprising Efficacy of LLMs for Penetration-Testing Gpts are gpts: Labor market impact potential of llms

Reference 22

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.427808Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 351a2e6a-ccff-421d-9007-946b0c54f360 · outbound

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

On the Surprising Efficacy of LLMs for Penetration-Testing LLM Agents can Autonomously Exploit One-day Vulnerabilities

Reference 23

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.432005Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7f7d507f-19ff-43c2-8dca-6943b95dbe52 · outbound

This paper cites Llm agents can autonomously hack websites, 2024.

On the Surprising Efficacy of LLMs for Penetration-Testing Llm agents can autonomously hack websites, 2024

Reference 24

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.436415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fac21925-22f5-4eca-b4be-f76d5119c601 · outbound

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

On the Surprising Efficacy of LLMs for Penetration-Testing Teams of LLM Agents can Exploit Zero-Day Vulnerabilities

Reference 25

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.440364Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a63c52cf-7bc2-4218-b509-de8ffb86a80a · outbound

This paper cites Wormgpt: a large language model chatbot for criminals.

On the Surprising Efficacy of LLMs for Penetration-Testing Wormgpt: a large language model chatbot for criminals

Reference 26

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.445121Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 3cd811ee-0138-4314-8cbd-db11bcedce08 · outbound

This paper cites Who’s asking? user personas and the mechanics of latent misalignment.

On the Surprising Efficacy of LLMs for Penetration-Testing Who’s asking? user personas and the mechanics of latent misalignment

Reference 27

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.451499Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 4d7d9d3d-5ce4-418b-a742-22dd271fc41d · outbound

This paper cites AutoPenBench: Benchmarking Generative Agents for Penetration Testing.

On the Surprising Efficacy of LLMs for Penetration-Testing AutoPenBench: Benchmarking Generative Agents for Penetration Testing

Reference 28

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.455902Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 352318db-05e8-4bc1-a136-2a0e310be3ba · outbound

This paper cites Project naptime: Evaluating offensive security capabilities of large language models.

On the Surprising Efficacy of LLMs for Penetration-Testing Project naptime: Evaluating offensive security capabilities of large language models

Reference 29

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.460359Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ac7dec3a-805f-4039-b198-e63a9802c4f9 · outbound

This paper cites Adversarial misuse of generative ai.

On the Surprising Efficacy of LLMs for Penetration-Testing Adversarial misuse of generative ai

Reference 30

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.464783Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b1a09501-8220-4633-b105-9be022bec520 · outbound

This paper cites A Survey on LLM-as-a-Judge.

On the Surprising Efficacy of LLMs for Penetration-Testing A Survey on LLM-as-a-Judge

Reference 31

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.470704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 575a2042-aec6-40b3-b019-087c8aebb908 · outbound

This paper cites How we built our multi-agent research system.

On the Surprising Efficacy of LLMs for Penetration-Testing How we built our multi-agent research system

Reference 32

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.476893Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 82093bb9-bcdb-4380-af6e-0a3aa0f4ac5e · outbound

This paper cites Getting pwn’d by ai: Penetration testing with large language models.

On the Surprising Efficacy of LLMs for Penetration-Testing Getting pwn’d by ai: Penetration testing with large language models

Reference 33

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.482642Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation b64cde0e-e664-414b-892a-6ce2c38a81d6 · outbound

This paper cites Understanding hackers’ work: An empirical study of offensive security practitioners.

On the Surprising Efficacy of LLMs for Penetration-Testing Understanding hackers’ work: An empirical study of offensive security practitioners

Reference 34

Resolution: metadata mismatch; raw_fallback, observed 2026-08-06T21:10:08.744071Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation bed81608-05d1-4c89-a81a-27894b52f624 · outbound

This paper cites Benchmarking Practices in LLM-driven Offensive Security: Testbeds, Metrics, and Experiment Design.

On the Surprising Efficacy of LLMs for Penetration-Testing Benchmarking Practices in LLM-driven Offensive Security: Testbeds, Metrics, and Experiment Design

Reference 35

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.491227Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5409c3b5-13cd-4e16-a2a8-3d490009a0f6 · outbound

This paper cites Recognition Without Mitigation: Ethical Frameworks in Autonomous Offensive-LLM Agent Research.

On the Surprising Efficacy of LLMs for Penetration-Testing Recognition Without Mitigation: Ethical Frameworks in Autonomous Offensive-LLM Agent Research

Reference 36

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:10:08.637385Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7232b88f-5019-4a15-b0b6-63694ce69ce9 · outbound

This paper cites Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks.

On the Surprising Efficacy of LLMs for Penetration-Testing Can LLMs Hack Enterprise Networks? Autonomous Assumed Breach Penetration-Testing Active Directory Networks

Reference 37

Resolution: verified exact; local_arxiv, observed 2026-08-06T21:10:08.622015Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7ca824d5-1b66-4f31-a69c-4bc534fafbc1 · outbound

This paper cites Llms as hackers: Autonomous linux privilege escalation attacks.

On the Surprising Efficacy of LLMs for Penetration-Testing Llms as hackers: Autonomous linux privilege escalation attacks

Reference 38

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.508012Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 824535aa-baff-4a58-9a00-e3275372f47e · outbound

This paper cites A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions.

On the Surprising Efficacy of LLMs for Penetration-Testing A Comprehensive Overview of Large Language Models (LLMs) for Cyber Defences: Opportunities and Directions

Reference 39

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.514085Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d885cf06-eb21-412e-b80c-2f725fe7200c · outbound

This paper cites Does prompt formatting have any impact on llm performance?,.

On the Surprising Efficacy of LLMs for Penetration-Testing Does prompt formatting have any impact on llm performance?,

Reference 40

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.520107Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a756b40d-d815-44d0-aa17-4e521e5cb53d · outbound

This paper cites How i used o3 to find cve-2025-37899, a remote zeroday vulnerability in the linux kernel’s smb implementation.

On the Surprising Efficacy of LLMs for Penetration-Testing How i used o3 to find cve-2025-37899, a remote zeroday vulnerability in the linux kernel’s smb implementation

Reference 41

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.528878Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7d980772-7ee5-44f6-83a5-9fd4bb7610d1 · outbound

This paper cites Ai and the increase of productivity and labor inequality in latin america: Potential impact of large language models on latin american workforce.

On the Surprising Efficacy of LLMs for Penetration-Testing Ai and the increase of productivity and labor inequality in latin america: Potential impact of large language models on latin american workforce

Reference 42

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.533037Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9a2fb4a9-d0b9-401d-bd66-52ba8e377ad2 · outbound

This paper cites Does Prompt Formatting Have Any Impact on LLM Performance?.

On the Surprising Efficacy of LLMs for Penetration-Testing Does Prompt Formatting Have Any Impact on LLM Performance?

Reference 43

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.524128Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 934cfb72-d162-4124-9093-7f5d8f904889 · outbound

This paper cites Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations.

On the Surprising Efficacy of LLMs for Penetration-Testing Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations

Reference 44

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.541993Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 1a4bd8c7-32bd-4450-b98b-9d9485beea19 · outbound

This paper cites Ethics and algorithms.

On the Surprising Efficacy of LLMs for Penetration-Testing Ethics and algorithms

Reference 45

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.510114Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d83347f0-7bba-4c01-9f4f-d1c037e52658 · outbound

This paper cites Uncertainty of thoughts: Uncertainty-aware planning enhances information seeking in llms.

On the Surprising Efficacy of LLMs for Penetration-Testing Uncertainty of thoughts: Uncertainty-aware planning enhances information seeking in llms

Reference 46

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:04.537340Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ef64c1d6-acf3-4aa8-9cef-9c39043fc37d · outbound

This paper cites How hungry is ai? benchmarking energy, water, and carbon footprint of llm inference, 2025.

On the Surprising Efficacy of LLMs for Penetration-Testing How hungry is ai? benchmarking energy, water, and carbon footprint of llm inference, 2025

Reference 47

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.517346Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 97326b02-7ed5-4e50-893f-3bacf69d6168 · outbound

This paper cites From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future.

On the Surprising Efficacy of LLMs for Penetration-Testing From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future

Reference 48

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.520524Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2c901dc0-205b-44f7-bba4-f82be3990337 · outbound

This paper cites 2024 isc2 cybersecurity workforce study.

On the Surprising Efficacy of LLMs for Penetration-Testing 2024 isc2 cybersecurity workforce study

Reference 49

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.513269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 76e18fe3-4ef6-465a-bae8-ea273ed2ea40 · outbound

This paper cites Advances in llms with focus on reasoning, adaptability, efficiency and ethics.

On the Surprising Efficacy of LLMs for Penetration-Testing Advances in llms with focus on reasoning, adaptability, efficiency and ethics

Reference 50

Resolution: verified exact; raw_fallback, observed 2026-08-06T21:10:08.412919Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0e6b257d-38d6-4045-8e09-46aa422153ac · outbound

This paper cites A survey of llm-driven ai agent communication: Protocols, security risks, and defense countermeasures, 2025.

On the Surprising Efficacy of LLMs for Penetration-Testing A survey of llm-driven ai agent communication: Protocols, security risks, and defense countermeasures, 2025

Reference 51

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.530477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8ef0c43c-fd67-4030-b82a-de8f52a34551 · outbound

This paper cites Generation, Detection, and Evaluation of Role-play based Jailbreak attacks in Large Language Models.

On the Surprising Efficacy of LLMs for Penetration-Testing Generation, Detection, and Evaluation of Role-play based Jailbreak attacks in Large Language Models

Reference 52

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.523847Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d76cb56b-025a-4ac3-8a7b-1f5937f3182a · outbound

This paper cites Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task.

On the Surprising Efficacy of LLMs for Penetration-Testing Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Task

Reference 53

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.537095Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 38a60a22-f8bf-4d99-bd1c-d079e507966f · outbound

This paper cites Revolutionizing talent: the path in 21st century workforce transformation.

On the Surprising Efficacy of LLMs for Penetration-Testing Revolutionizing talent: the path in 21st century workforce transformation

Reference 54

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.540785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5f620134-4133-4460-ac39-cd37a3c7b458 · outbound

This paper cites VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework.

On the Surprising Efficacy of LLMs for Penetration-Testing VulnBot: Autonomous Penetration Testing for A Multi-Agent Collaborative Framework

Reference 55

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.533634Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9770da71-26cb-4f25-824d-f95688174039 · outbound

This paper cites Shade-arena: Evaluating sabotage and monitoring in llm agents.

On the Surprising Efficacy of LLMs for Penetration-Testing Shade-arena: Evaluating sabotage and monitoring in llm agents

Reference 56

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.547704Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a943492c-c5fc-4534-b50c-a02ab8c4a18e · outbound

This paper cites LLMs Get Lost In Multi-Turn Conversation.

On the Surprising Efficacy of LLMs for Penetration-Testing LLMs Get Lost In Multi-Turn Conversation

Reference 57

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.551304Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 753acd2e-50e0-4d0b-9b36-9024c953804f · outbound

This paper cites an unresolved cited work.

On the Surprising Efficacy of LLMs for Penetration-Testing Unresolved cited work

Reference 58

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.544515Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 941fbd55-c03d-4a9b-a1b9-8e0f023b5ed1 · outbound

This paper cites Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?.

On the Surprising Efficacy of LLMs for Penetration-Testing Can Long-Context Language Models Subsume Retrieval, RAG, SQL, and More?

Reference 59

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.558326Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 73e34ba9-3a85-4509-baa3-3fe265b8d32f · outbound

This paper cites I think i’m done thinking about genai for now.

On the Surprising Efficacy of LLMs for Penetration-Testing I think i’m done thinking about genai for now

Reference 60

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.562357Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation d6943c7f-25d7-4208-8584-8dea67852ca9 · outbound

This paper cites Operating multi-client influ- ence networks across platforms.

On the Surprising Efficacy of LLMs for Penetration-Testing Operating multi-client influ- ence networks across platforms

Reference 61

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.555475Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 9f76e63d-8118-4da8-88da-7a5654e0c337 · outbound

This paper cites Malla: Demystifying real-world large language model integrated malicious services.

On the Surprising Efficacy of LLMs for Penetration-Testing Malla: Demystifying real-world large language model integrated malicious services

Reference 62

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.571200Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation cdbc0a5f-136d-49ff-833f-e1e91ac638f3 · outbound

This paper cites Ai-powered fuzzing: Breaking the bug hunting barrier.

On the Surprising Efficacy of LLMs for Penetration-Testing Ai-powered fuzzing: Breaking the bug hunting barrier

Reference 63

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.574294Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 6cfbdbc0-3553-41da-9d06-9a8b602012f7 · outbound

This paper cites an unresolved cited work.

On the Surprising Efficacy of LLMs for Penetration-Testing Unresolved cited work

Reference 64

Resolution: parse uncertain; no resolver link, observed 2026-08-06T21:10:06.565216Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f6d90882-42a1-4a02-9b4d-b17aaff211e0 · outbound

This paper cites When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs.

On the Surprising Efficacy of LLMs for Penetration-Testing When Thinking Fails: The Pitfalls of Reasoning for Instruction-Following in LLMs

Reference 65

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.568134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation fd554f45-1f6a-4fd8-aacf-30328e9f2855 · outbound

This paper cites Troy, Stuart J.

On the Surprising Efficacy of LLMs for Penetration-Testing Troy, Stuart J

Reference 66

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.582782Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 5a67be7a-4fcd-46e8-b0bd-2665d1676dc3 · outbound

This paper cites Llm dataset inference: Did you train on my dataset? Advances in Neural Information Pro- cessing Systems, 37:124069–124092, 2024.

On the Surprising Efficacy of LLMs for Penetration-Testing Llm dataset inference: Did you train on my dataset? Advances in Neural Information Pro- cessing Systems, 37:124069–124092, 2024

Reference 67

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.585900Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2064aa91-2129-48b3-b60f-39c01393918b · outbound

This paper cites LLM Cyber Evaluations Don't Capture Real-World Risk.

On the Surprising Efficacy of LLMs for Penetration-Testing LLM Cyber Evaluations Don't Capture Real-World Risk

Reference 68

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.577088Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 527d6ca1-fbff-49aa-a0de-c5a81fee8ce2 · outbound

This paper cites The dual-use security dilemma and the social construction of insecurity.

On the Surprising Efficacy of LLMs for Penetration-Testing The dual-use security dilemma and the social construction of insecurity

Reference 69

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.579914Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 7a73bf9f-fdc7-4f23-8b9d-8ec1da972092 · outbound

This paper cites Llama prompt guard 2.

On the Surprising Efficacy of LLMs for Penetration-Testing Llama prompt guard 2

Reference 70

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.329925Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation f0a075df-f788-413b-b3d5-1ec21f4e1f96 · outbound

This paper cites Large Language Models as General Pattern Machines.

On the Surprising Efficacy of LLMs for Penetration-Testing Large Language Models as General Pattern Machines

Reference 71

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.598563Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8cdebbe3-21a2-4fd5-8731-bdc14bbde1f4 · outbound

This paper cites Why using chatgpt is not bad for the environment - a cheat sheet.

On the Surprising Efficacy of LLMs for Penetration-Testing Why using chatgpt is not bad for the environment - a cheat sheet

Reference 72

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.339592Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 662b7cca-2024-463e-bec2-9520076fd46b · outbound

This paper cites Mavikumbure, Victor Cobilean, Chathurika S.

On the Surprising Efficacy of LLMs for Penetration-Testing Mavikumbure, Victor Cobilean, Chathurika S

Reference 73

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.592249Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation f02c66bd-d8c0-4d03-ab22-6e32659f1f97 · outbound

This paper cites Large Language Models in Cybersecurity: State-of-the-Art.

On the Surprising Efficacy of LLMs for Penetration-Testing Large Language Models in Cybersecurity: State-of-the-Art

Reference 74

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.607291Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation ca887944-91c6-436c-ad1f-c28a8bb08463 · outbound

This paper cites Influence and cyber operations: an up- date.

On the Surprising Efficacy of LLMs for Penetration-Testing Influence and cyber operations: an up- date

Reference 75

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.300190Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 698337fb-0bdc-415a-8372-a560aa84f6cf · outbound

This paper cites The threat of offensive ai to organizations.

On the Surprising Efficacy of LLMs for Penetration-Testing The threat of offensive ai to organizations

Reference 76

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.319250Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8c162f27-3027-4da3-b2d9-3a43952d4639 · outbound

This paper cites Global ransomware damage costs predicted to exceed $275 billion by 2031.

On the Surprising Efficacy of LLMs for Penetration-Testing Global ransomware damage costs predicted to exceed $275 billion by 2031

Reference 77

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.309051Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0e0b8246-7a41-489c-a403-b45879be233b · outbound

This paper cites Introducting chatgpt.

On the Surprising Efficacy of LLMs for Penetration-Testing Introducting chatgpt

Reference 78

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.272572Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 0790fb15-a216-4c14-aa4a-318c8af564b9 · outbound

This paper cites Introducing openai o1.

On the Surprising Efficacy of LLMs for Penetration-Testing Introducing openai o1

Reference 79

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.258320Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 7c54e393-af43-4a89-82e9-72d3fe751ce9 · outbound

This paper cites Disrupting malicious uses of ai: June 2025.

On the Surprising Efficacy of LLMs for Penetration-Testing Disrupting malicious uses of ai: June 2025

Reference 80

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.290340Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 4f70c9e9-1810-44ec-9fbe-c06c02ded2a1 · outbound

This paper cites Disrupting malicious uses of ai: February 2025.

On the Surprising Efficacy of LLMs for Penetration-Testing Disrupting malicious uses of ai: February 2025

Reference 81

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.281540Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 571dd12d-aa7e-403e-bd5d-1c666edd50f7 · outbound

This paper cites Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad.

On the Surprising Efficacy of LLMs for Penetration-Testing Proof or Bluff? Evaluating LLMs on 2025 USA Math Olympiad

Reference 82

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.635014Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation efb000e8-90cc-4a31-a9cf-7692ecbdea01 · outbound

This paper cites Cipher: Cyberse- curity intelligent penetration-testing helper for ethical researcher.

On the Surprising Efficacy of LLMs for Penetration-Testing Cipher: Cyberse- curity intelligent penetration-testing helper for ethical researcher

Reference 83

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.232584Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 459fd750-7c0a-4363-948f-c74a99703929 · outbound

This paper cites My ai skeptic friends are all nuts.

On the Surprising Efficacy of LLMs for Penetration-Testing My ai skeptic friends are all nuts

Reference 84

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.223421Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ee14fad6-56cc-4a15-b823-0e4e40406d1a · outbound

This paper cites Disrupting malicious uses of ai by state-affiliated threat actors.

On the Surprising Efficacy of LLMs for Penetration-Testing Disrupting malicious uses of ai by state-affiliated threat actors

Reference 85

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.250034Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 1b63a2a8-0fb5-4b1a-97ad-5252ff786855 · outbound

This paper cites Annual share of organizations affected by ransomware at- tacks worldwide from 2018 to 2023.

On the Surprising Efficacy of LLMs for Penetration-Testing Annual share of organizations affected by ransomware at- tacks worldwide from 2018 to 2023

Reference 86

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.241453Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 2a2862cf-5373-44b2-9608-044e88ade227 · outbound

This paper cites Anderson, Edward W.

On the Surprising Efficacy of LLMs for Penetration-Testing Anderson, Edward W

Reference 87

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.653621Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation a0e3fa75-76a2-41c3-a90e-714a8f0405ac · outbound

This paper cites An Empirical Evaluation of LLMs for Solving Offensive Security Challenges.

On the Surprising Efficacy of LLMs for Penetration-Testing An Empirical Evaluation of LLMs for Solving Offensive Security Challenges

Reference 88

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.656665Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c5fa02d9-f373-44db-93ea-6c0320e3148e · outbound

This paper cites Future of work with ai agents: Auditing automation and augmentation potential across the u.s.

On the Surprising Efficacy of LLMs for Penetration-Testing Future of work with ai agents: Auditing automation and augmentation potential across the u.s

Reference 89

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.660064Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 2cddee42-f3aa-4465-9b39-adbb27e6b83c · outbound

This paper cites Complementarity, Augmentation, or Substitutivity? The Impact of Generative Artificial Intelligence on the U.S. Federal Workforce.

On the Surprising Efficacy of LLMs for Penetration-Testing Complementarity, Augmentation, or Substitutivity? The Impact of Generative Artificial Intelligence on the U.S. Federal Workforce

Reference 90

Resolution: metadata mismatch; local_arxiv, observed 2026-08-06T21:10:08.097671Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation cfeb8941-1cb2-47e7-ad14-f552855b4ab5 · outbound

This paper cites Llm-based design pattern detection,.

On the Surprising Efficacy of LLMs for Penetration-Testing Llm-based design pattern detection,

Reference 91

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.214551Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation d446b817-71c4-460d-93c4-1843012c972e · outbound

This paper cites LLM-Based Design Pattern Detection.

On the Surprising Efficacy of LLMs for Penetration-Testing LLM-Based Design Pattern Detection

Reference 92

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.651054Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 37b9e362-dabc-4594-9cf4-593d5dadabd0 · outbound

This paper cites Announcing the agent2agent protocol (a2a).

On the Surprising Efficacy of LLMs for Penetration-Testing Announcing the agent2agent protocol (a2a)

Reference 93

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.194465Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 474c657b-c803-4db8-a3d6-ed2534922675 · outbound

This paper cites Systematic Biases in LLM Simulations of Debates.

On the Surprising Efficacy of LLMs for Penetration-Testing Systematic Biases in LLM Simulations of Debates

Reference 94

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.675136Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation 8c6994cc-c998-441c-937c-3c9232052e30 · outbound

This paper cites From naptime to big sleep: Using large language models to catch vulnerabilities in real-world code.

On the Surprising Efficacy of LLMs for Penetration-Testing From naptime to big sleep: Using large language models to catch vulnerabilities in real-world code

Reference 95

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.184325Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8ebe2604-da0a-468a-89dd-3d2cc62a406f · outbound

This paper cites The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity.

On the Surprising Efficacy of LLMs for Penetration-Testing The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

Reference 96

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.662541Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation e79bed61-a8e8-4bd1-8b9b-dc0e8799e91b · outbound

This paper cites On the feasibility of using llms to execute multistage network attacks.

On the Surprising Efficacy of LLMs for Penetration-Testing On the feasibility of using llms to execute multistage network attacks

Reference 97

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.666134Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Observation c04cfdd0-1812-4a2e-8697-2babd1f60407 · outbound

This paper cites Outside the closed world: On using machine learning for network intrusion detection.

On the Surprising Efficacy of LLMs for Penetration-Testing Outside the closed world: On using machine learning for network intrusion detection

Reference 98

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.204429Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation ec2808ef-23f9-4135-add9-3963cb3bcf77 · outbound

This paper cites Rainbows End: A Novel With One Foot In The Future.

On the Surprising Efficacy of LLMs for Penetration-Testing Rainbows End: A Novel With One Foot In The Future

Reference 99

Resolution: verified fuzzy; raw_fallback, observed 2026-08-06T21:10:09.150860Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.

Observation 8ae6a063-c6fc-4d39-824d-bb6363b39682 · outbound

This paper cites "Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters.

On the Surprising Efficacy of LLMs for Penetration-Testing "Kelly is a Warm Person, Joseph is a Role Model": Gender Biases in LLM-Generated Reference Letters

Reference 100

Resolution: unresolved; no resolver link, observed 2026-08-06T21:10:06.693153Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

Coverage vector

Reference resolution

Outbound references

Pith citing papers