---
title: "AI Pentesting Tools & Cybersecurity Research | 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"
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/)
- [Next](https://paperswithcode-cyber.com/catalog?offset=25)

## Relevant papers

1. [CyberDual: AI Attackers versus AI Code Reviewers in Real\-World Software Maintenance](https://paperswithcode-cyber.com/paper/2610.34435) — 2026 · Benchmark
2. [CyberArena: Benchmarking AI Agents in Live Symmetric Attack\-and\-Defense Combat](https://paperswithcode-cyber.com/paper/2610.19005) — 2026 · Benchmark
3. [CheckerBench: Can Long\-Horizon Agents Synthesize Static\-Analysis Checkers?](https://paperswithcode-cyber.com/paper/2610.07557) — 2026 · Benchmark
4. [KaliBench: A Fine\-Grained Benchmark for Cybersecurity Tool Use on Kali Linux with Runtime\-Free Verifiable Rewards](https://paperswithcode-cyber.com/paper/2610.02206) — 2026 · Benchmark · Dataset
5. [CyberPersistBench: Evaluating LLM\-Based Cyber Attackers on Installation and Persistence](https://paperswithcode-cyber.com/paper/2609.36573) — 2026 · Benchmark
6. [Where Cyber Agents Struggle: Bottleneck Analysis of Multi\-Stage LLM Agents](https://paperswithcode-cyber.com/paper/2609.28572) — 2026 · Empirical study / experience
7. [Rouxii: Exploiting Honeypots with Deception\-Aware AI Pentesters](https://paperswithcode-cyber.com/paper/2609.26555) — 2026 · System or technique · Empirical study / experience
8. [MobileCybench: Evaluating Agent Vulnerability Discovery via Executable Probes](https://paperswithcode-cyber.com/paper/2609.23980) — 2026 · Benchmark
9. [Auditing in the age of \(good enough\) AI](https://paperswithcode-cyber.com/paper/319) — 2026 · Empirical study / experience
10. [PentestChain: A Cost\-Aware, MCP\-Orchestrated Framework for Automated Penetration Testing with Free\-Tier LLMs](https://paperswithcode-cyber.com/paper/2609.18120) — 2026 · System or technique
11. [Automating Attack Graph Construction for Agentic Pentesting\. Towards Neuro\-Symbolic Vulnerability Hunting](https://paperswithcode-cyber.com/paper/2609.15523) — 2026 · System or technique
12. [Beltdown: Escaping the Claude Code sandbox](https://paperswithcode-cyber.com/paper/321) — 2026 · Empirical study / experience
13. [LLM\-Based Agents for Cybersecurity: A Systematic Review of Architectures, Applications, and Open Challenges](https://paperswithcode-cyber.com/paper/93) — 2026 · Survey / review
14. [PrivEscalate: Measuring and Augmenting the Threat of LLM\-Automated Linux Privilege Escalation](https://paperswithcode-cyber.com/paper/2609.09087) — 2026 · Benchmark · System or technique
15. [VEX\-Bench: Benchmarking LLM Agents for Assessing Exploitability of Software Supply Chain Vulnerabilities](https://paperswithcode-cyber.com/paper/2609.08040) — 2026 · Benchmark
16. [How River takes security work from a fix to merge](https://paperswithcode-cyber.com/paper/318) — 2026 · System or technique
17. [Booz Allen Cyber Weapon Index](https://paperswithcode-cyber.com/paper/323) — 2026 · Benchmark
18. [FuzzingBrain\-Bench V1: Evaluating Open\-Ended Bug Discovery by LLMs](https://paperswithcode-cyber.com/paper/2608.25158) — 2026 · Benchmark
19. [Patterns and problems in emerging multiagent systems](https://paperswithcode-cyber.com/paper/322) — 2026 · Empirical study / experience
20. [Large language models\-driven fuzzing: A systematic survey](https://paperswithcode-cyber.com/paper/98) — 2026 · Survey / review