ExploitGym: Can AI agents turn bugs into exploits?

p_stuart821 pts0 comments

[2605.11086] ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

-->

Computer Science > Cryptography and Security

arXiv:2605.11086 (cs)

[Submitted on 11 May 2026]

Title:ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?

Authors:Zhun Wang, Nico Schiller, Hongwei Li, Srijiith Sesha Narayana, Milad Nasr, Nicholas Carlini, Xiangyu Qi, Eric Wallace, Elie Bursztein, Luca Invernizzi, Kurt Thomas, Yan Shoshitaishvili, Wenbo Guo, Jingxuan He, Thorsten Holz, Dawn Song<br>View a PDF of the paper titled ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?, by Zhun Wang and 15 other authors

View PDF<br>HTML (experimental)

Abstract:AI agents are rapidly gaining capabilities that could significantly reshape cybersecurity, making rigorous evaluation urgent. A critical capability is exploitation: turning a vulnerability, which is not yet an attack, into a concrete security impact, such as unauthorized file access or code execution. Exploitation is a particularly challenging task because it requires low-level program reasoning (e.g., about memory layout), runtime adaptation, and sustained progress over long horizons. Meanwhile, it is inherently dual-use, supporting defensive workflows while lowering the barrier for offense. Despite its importance and diagnostic value, exploitation remains under-evaluated. To address this gap, we introduce ExploitGym, a large-scale, diverse, realistic benchmark on the exploitation capabilities of AI agents. Given a program input that triggers a vulnerability, ExploitGym tasks agents with progressively extending it into a working exploit. The benchmark comprises 898 instances sourced from real-world vulnerabilities across three domains, including userspace programs, Google's V8 JavaScript engine, and the Linux kernel. We vary the security protections applied to each instance, isolating their impact on agent performance. All configurations are packaged in reproducible containerized environments. Our evaluation shows that while exploitation remains challenging, frontier models can successfully exploit a non-trivial fraction of vulnerabilities. For example, the strongest configurations are Anthropic's latest model Claude Mythos Preview and OpenAI's GPT-5.5, which produce working exploits for 157 and 120 instances, respectively. Notably, even with widely used defenses enabled, models retain non-trivial success rates. These results establish ExploitGym as an effective testbed for exploitation and highlight the growing cybersecurity risks posed by increasingly capable AI agents.

Subjects:

Cryptography and Security (cs.CR); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Cite as:<br>arXiv:2605.11086 [cs.CR]

(or<br>arXiv:2605.11086v1 [cs.CR] for this version)

https://doi.org/10.48550/arXiv.2605.11086

Focus to learn more

arXiv-issued DOI via DataCite (pending registration)

Submission history<br>From: Zhun Wang [view email]<br>[v1]<br>Mon, 11 May 2026 18:00:14 UTC (629 KB)

Full-text links:<br>Access Paper:

View a PDF of the paper titled ExploitGym: Can AI Agents Turn Security Vulnerabilities into Real Attacks?, by Zhun Wang and 15 other authors<br>View PDF<br>HTML (experimental)<br>TeX Source

view license

Current browse context:

cs.CR

next >

new<br>recent<br>| 2026-05

Change to browse by:

cs<br>cs.AI<br>cs.LG

References & Citations

NASA ADS<br>Google Scholar

Semantic Scholar

export BibTeX citation<br>Loading...

BibTeX formatted citation

&times;

loading...

Data provided by:

Bookmark

Bibliographic Tools

Bibliographic and Citation Tools

Bibliographic Explorer Toggle

Bibliographic Explorer (What is the Explorer?)

Connected Papers Toggle

Connected Papers (What is Connected Papers?)

Litmaps Toggle

Litmaps (What is Litmaps?)

scite.ai Toggle

scite Smart Citations (What are Smart Citations?)

Code, Data, Media

Code, Data and Media Associated with this Article

alphaXiv Toggle

alphaXiv (What is alphaXiv?)

Links to Code Toggle

CatalyzeX Code Finder for Papers (What is CatalyzeX?)

DagsHub Toggle

DagsHub (What is DagsHub?)

GotitPub Toggle

Gotit.pub (What is GotitPub?)

Huggingface Toggle

Hugging Face (What is Huggingface?)

ScienceCast Toggle

ScienceCast (What is ScienceCast?)

Demos

Demos

Replicate Toggle

Replicate (What is Replicate?)

Spaces Toggle

Hugging Face Spaces (What is Spaces?)

Spaces Toggle

TXYZ.AI (What is TXYZ.AI?)

Related Papers

Recommenders and Search Tools

Link to Influence Flower

Influence Flower (What are Influence Flowers?)

Core recommender toggle

CORE Recommender (What is CORE?)

Author

Venue

Institution

Topic

About arXivLabs

arXivLabs: experimental projects with community collaborators

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and...

toggle agents exploitgym security arxiv vulnerabilities

Related Articles