SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917548826558464 |
|---|---|
| author | Zhang, Cen Park, Younggi Fleischer, Fabian Fu, Yu-Fu Kim, Jiho Kim, Dongkwan Kim, Youngjoon Xu, Qingxiao Chin, Andrew Sheng, Ze Zhao, Hanqing Pelican, Michael Musliner, David J. Huang, Jeff Silliman, Jon Mcdaniel, Mikel Casavant, Jefferson Goldthwaite, Isaac Vidovich, Nicholas Lehman, Matthew Kim, Taesoo |
| author_facet | Zhang, Cen Park, Younggi Fleischer, Fabian Fu, Yu-Fu Kim, Jiho Kim, Dongkwan Kim, Youngjoon Xu, Qingxiao Chin, Andrew Sheng, Ze Zhao, Hanqing Pelican, Michael Musliner, David J. Huang, Jeff Silliman, Jon Mcdaniel, Mikel Casavant, Jefferson Goldthwaite, Isaac Vidovich, Nicholas Lehman, Matthew Kim, Taesoo |
| contents | DARPA's AI Cyber Challenge (AIxCC, 2023--2025) is the largest competition to date for building fully autonomous cyber reasoning systems (CRSs) that leverage recent advances in AI -- particularly large language models (LLMs) -- to discover and remediate vulnerabilities in real-world open-source software. This paper presents the first systematic analysis of AIxCC. Drawing on design documents, source code, execution traces, and discussions with organizers and competing teams, we examine the competition's structure and key design decisions, characterize the architectural approaches of finalist CRSs, and analyze competition results beyond the final scoreboard. Our analysis reveals the factors that truly drove CRS performance, identifies genuine technical advances achieved by teams, and exposes limitations that remain open for future research. We conclude with lessons for organizing future competitions and broader insights toward deploying autonomous CRSs in practice. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_07666 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned Zhang, Cen Park, Younggi Fleischer, Fabian Fu, Yu-Fu Kim, Jiho Kim, Dongkwan Kim, Youngjoon Xu, Qingxiao Chin, Andrew Sheng, Ze Zhao, Hanqing Pelican, Michael Musliner, David J. Huang, Jeff Silliman, Jon Mcdaniel, Mikel Casavant, Jefferson Goldthwaite, Isaac Vidovich, Nicholas Lehman, Matthew Kim, Taesoo Cryptography and Security Artificial Intelligence DARPA's AI Cyber Challenge (AIxCC, 2023--2025) is the largest competition to date for building fully autonomous cyber reasoning systems (CRSs) that leverage recent advances in AI -- particularly large language models (LLMs) -- to discover and remediate vulnerabilities in real-world open-source software. This paper presents the first systematic analysis of AIxCC. Drawing on design documents, source code, execution traces, and discussions with organizers and competing teams, we examine the competition's structure and key design decisions, characterize the architectural approaches of finalist CRSs, and analyze competition results beyond the final scoreboard. Our analysis reveals the factors that truly drove CRS performance, identifies genuine technical advances achieved by teams, and exposes limitations that remain open for future research. We conclude with lessons for organizing future competitions and broader insights toward deploying autonomous CRSs in practice. |
| title | SoK: DARPA's AI Cyber Challenge (AIxCC): Competition Design, Architectures, and Lessons Learned |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2602.07666 |