---
title: "AI Pentesting Tools & Cybersecurity Research — Page 6 | 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=125"
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=100)
- [Next](https://paperswithcode-cyber.com/catalog?offset=150)

## Relevant papers

1. [CYBERSECEVAL 3: Advancing the Evaluation of Cybersecurity Risks and Capabilities in Large Language Models](https://paperswithcode-cyber.com/paper/2408.01605) — 2024 · Benchmark
2. [From Sands to Mansions: Actionable, Customizable and Causality\-Preserving Cyberattack Emulation with LLM\-powered Symbolic Planning](https://paperswithcode-cyber.com/paper/2407.16928) — 2024 · Dataset · System or technique
3. [NYU CTF Bench: A Scalable Open\-Source Benchmark Dataset for Evaluating LLMs in Offensive Security](https://paperswithcode-cyber.com/paper/61) — 2024 · System or technique · Benchmark · Dataset
4. [CyberSecEval 2: A Wide\-Ranging Cybersecurity Evaluation Suite for Large Language Models](https://paperswithcode-cyber.com/paper/2404.13161) — 2024 · Benchmark
5. [LLM Agents can Autonomously Exploit One\-day Vulnerabilities](https://paperswithcode-cyber.com/paper/58) — 2024 · System or technique · Benchmark · Empirical study / experience
6. [Fuzzing BusyBox: Leveraging LLM and Crash Reuse for Embedded Bug Unearthing](https://paperswithcode-cyber.com/paper/79) — 2024 · System or technique · Empirical study / experience
7. [An Empirical Evaluation of LLMs for Solving Offensive Security Challenges](https://paperswithcode-cyber.com/paper/2402.11814) — 2024 · Empirical study / experience
8. [Large Language Models are Edge\-Case Generators: Crafting Unusual Programs for Fuzzing Deep Learning Libraries](https://paperswithcode-cyber.com/paper/64) — 2024 · System or technique
9. [Large Language Model guided Protocol Fuzzing](https://paperswithcode-cyber.com/paper/63) — 2024 · System or technique
10. [KernelGPT: Enhanced Kernel Fuzzing via Large Language Models](https://paperswithcode-cyber.com/paper/2401.00563) — 2023 · System or technique
11. [WhiteFox: White\-Box Compiler Fuzzing Empowered by Large Language Models](https://paperswithcode-cyber.com/paper/77) — 2023 · System or technique
12. [LLMs as Hackers: Autonomous Linux Privilege Escalation Attacks](https://paperswithcode-cyber.com/paper/2310.11409) — 2023 · System or technique · Benchmark · Empirical study / experience
13. [Out of the Cage: How Stochastic Parrots Win in Cyber Security Environments](https://paperswithcode-cyber.com/paper/2308.12086) — 2023 · System or technique · Benchmark
14. [Getting pwn'd by AI: Penetration Testing with Large Language Models](https://paperswithcode-cyber.com/paper/57) — 2023 · System or technique · Empirical study / experience
15. [InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback](https://paperswithcode-cyber.com/paper/2306.14898) — 2023 · Benchmark
16. [PentestGPT: Evaluating and Harnessing Large Language Models for Automated Penetration Testing](https://paperswithcode-cyber.com/paper/56) — 2024 · System or technique · Benchmark · Empirical study / experience
17. [IRIS: LLM\-Assisted Static Analysis for Detecting Security Vulnerabilities](https://paperswithcode-cyber.com/paper/62) — 2024 · System or technique · Dataset · Benchmark
18. [LineVul: A Transformer\-based Line\-Level Vulnerability Prediction](https://paperswithcode-cyber.com/paper/71) — 2022 · System or technique
19. [Devign: Effective Vulnerability Identification by Learning Comprehensive Program Semantics via Graph Neural Networks](https://paperswithcode-cyber.com/paper/72) — 2019 · System or technique · Dataset
20. [VulDeePecker: A Deep Learning\-Based System for Vulnerability Detection](https://paperswithcode-cyber.com/paper/73) — 2018 · System or technique · Dataset