---
title: "AI Pentesting Tools & Cybersecurity Research — Page 2 | Papers With Code Cyber"
description: "Find AI pentesting tools, security agent harnesses, papers and benchmarks. Filter cybersecurity research by topic, target and contribution."
canonical: "https://paperswithcode-cyber.com/catalog?offset=25"
type: "catalog"
---

# Browse catalog

Find AI pentesting tools, security agent harnesses, papers and benchmarks\. Filter cybersecurity research by topic, target and contribution\. 189 papers\.

## Related research

- [Trending research](https://paperswithcode-cyber.com/)
- [Previous](https://paperswithcode-cyber.com/catalog)
- [Next](https://paperswithcode-cyber.com/catalog?offset=50)

## Relevant papers

1. [A Survey of LLM\-Driven Penetration Testing: Taxonomy, Co\-Evolution, and Open Challenges](https://paperswithcode-cyber.com/paper/92) — 2026 · Survey / review
2. [CyberChainBench: Can AI Agents Secure Smart Contracts Against Real\-World On\-Chain Vulnerabilities?](https://paperswithcode-cyber.com/paper/2606.26216) — 2026 · Benchmark
3. [Red\-Teaming the Agentic Red\-Team](https://paperswithcode-cyber.com/paper/2606.24496) — 2026 · Empirical study / experience · System or technique
4. [Build your own vulnerability harness](https://paperswithcode-cyber.com/paper/314) — 2026 · System or technique
5. [cloudflare/security\-audit\-skill](https://paperswithcode-cyber.com/paper/325) — 2026 · System or technique
6. [OpenAnt: LLM\-Powered Vulnerability Discovery Through Code Decomposition, Adversarial Verification, and Dynamic Testing](https://paperswithcode-cyber.com/paper/2606.19149) — 2026 · System or technique
7. [SoK: AI\-Augmented Binary Reversing](https://paperswithcode-cyber.com/paper/97) — 2026 · Survey / review
8. [AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Ranges](https://paperswithcode-cyber.com/paper/2606.14295) — 2026 · Benchmark
9. [Defend against frontier cyber models: Cloudflare's architecture as customer zero](https://paperswithcode-cyber.com/paper/316) — 2026 · Empirical study / experience
10. [CyberGym\-E2E: Scalable Real\-World Benchmark for AI Agents' End\-to\-End Cybersecurity Capabilities](https://paperswithcode-cyber.com/paper/2606.04460) — 2026 · Benchmark
11. [SEC\-bench Pro: Can Language Models Solve Long\-Horizon Software Security Tasks?](https://paperswithcode-cyber.com/paper/2605.26548) — 2026 · Benchmark
12. [Quality\-Assured Fuzz Harness Generation via the Four Principles Framework](https://paperswithcode-cyber.com/paper/2605.21824) — 2026 · System or technique
13. [Project Glasswing: what Mythos showed us](https://paperswithcode-cyber.com/paper/315) — 2026 · Empirical study / experience
14. [FuzzAgent: Multi\-Agent System for End\-to\-End Evolutionary Library Fuzzing](https://paperswithcode-cyber.com/paper/2605.14431) — 2026 · System or technique
15. [ExploitBench: A Capability Ladder Benchmark for LLM Cybersecurity Agents](https://paperswithcode-cyber.com/paper/2605.14153) — 2026 · Benchmark
16. [Cochise: A Reference Harness for Autonomous Penetration Testing](https://paperswithcode-cyber.com/paper/2605.11671) — 2026 · System or technique · Dataset
17. [CTFusion: A CTF Based Benchmark for Evaluating LLM Agents via MCP](https://paperswithcode-cyber.com/paper/2605.11504) — 2026 · Benchmark
18. [From Controlled to the Wild: Evaluation of Pentesting Agents for the Real\-World](https://paperswithcode-cyber.com/paper/2605.10834) — 2026 · System or technique · Benchmark · Dataset
19. [ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?](https://paperswithcode-cyber.com/paper/2605.11086) — 2026 · Benchmark
20. [CyBiasBench: Benchmarking Bias in LLM Agents for Cyber\-Attack Scenarios](https://paperswithcode-cyber.com/paper/2605.07830) — 2026 · Benchmark