---
title: "AI Pentesting Tools & Cybersecurity Research — Page 3 | 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=50"
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?offset=25)
- [Next](https://paperswithcode-cyber.com/catalog?offset=75)

## Relevant papers

1. [CritBench: A Framework for Evaluating Cybersecurity Capabilities of Large Language Models in IEC 61850 Digital Substation Environments](https://paperswithcode-cyber.com/paper/2604.06019) — 2026 · Benchmark
2. [A Multi\-Agent Framework for Automated Exploit Generation with Constraint\-Guided Comprehension and Reflection](https://paperswithcode-cyber.com/paper/2604.05130) — 2026 · System or technique
3. [Vulnerability datasets for software security: A survey of existing resources, challenges, and future directions](https://paperswithcode-cyber.com/paper/99) — 2026 · Survey / review
4. [Bridging Code Property Graphs and Language Models for Program Analysis](https://paperswithcode-cyber.com/paper/2603.24837) — 2026 · System or technique
5. [STRIATUM\-CTF: A Protocol\-Driven Agentic Framework for General\-Purpose CTF Solving](https://paperswithcode-cyber.com/paper/2603.22577) — 2026 · System or technique
6. [Towards Reliable Local Security Agents: Verifiable Post\-Training for Linux Privilege Escalation](https://paperswithcode-cyber.com/paper/2603.17673) — 2026 · System or technique
7. [EVMbench: Evaluating AI Agents on Smart Contract Security](https://paperswithcode-cyber.com/paper/2603.04915) — 2026 · Benchmark · Dataset
8. [AWE: Adaptive Agents for Dynamic Web Penetration Testing](https://paperswithcode-cyber.com/paper/70) — 2026 · System or technique
9. [Quantifying Frontier LLM Capabilities for Container Sandbox Escape](https://paperswithcode-cyber.com/paper/2603.02277) — 2026 · Benchmark
10. [ICSSPulse: A Modular LLM\-Assisted Platform for Industrial Control System Penetration Testing](https://paperswithcode-cyber.com/paper/2602.20663) — 2026 · System or technique
11. [We proactively fixed \~100 security issues in 6 days with 0 humans](https://paperswithcode-cyber.com/paper/320) — 2026 · System or technique
12. [SoK: DARPA's AI Cyber Challenge \(AIxCC\): Competition Design, Architectures, and Lessons Learned](https://paperswithcode-cyber.com/paper/96) — 2026 · Survey / review
13. [Capture the Flags: Family\-Based Evaluation of Agentic LLMs via Semantics\-Preserving Transformations](https://paperswithcode-cyber.com/paper/2602.05523) — 2026 · Benchmark · System or technique
14. [CVE\-Factory: Scaling Expert\-Level Agentic Tasks for Code Security Vulnerability](https://paperswithcode-cyber.com/paper/2602.03012) — 2026 · System or technique · Benchmark · Dataset
15. [Sifting the Noise: A Comparative Study of LLM Agents in Vulnerability False Positive Filtering](https://paperswithcode-cyber.com/paper/2601.22952) — 2026 · Empirical study / experience
16. [LLM\-based Vulnerability Detection at Project Scale: An Empirical Study](https://paperswithcode-cyber.com/paper/2601.19239) — 2026 · Empirical study / experience
17. [RvB: Automating AI System Hardening via Iterative Red\-Blue Games](https://paperswithcode-cyber.com/paper/2601.19726) — 2026 · System or technique
18. [PatchIsland: Orchestration of LLM Agents for Continuous Vulnerability Repair](https://paperswithcode-cyber.com/paper/2601.17471) — 2026 · System or technique
19. [From Transactions to Exploits: Automated PoC Synthesis for Real\-World DeFi Attacks](https://paperswithcode-cyber.com/paper/2601.16681) — 2026 · System or technique
20. [SmartOracle \-\- An Agentic Approach to Mitigate Noise in Differential Oracles](https://paperswithcode-cyber.com/paper/2601.15074) — 2026 · System or technique