Research

Paper

AI LLM March 09, 2026

OSS-CRS: Liberating AIxCC Cyber Reasoning Systems for Real-World Open-Source Security

Authors

Andrew Chin, Dongkwan Kim, Yu-Fu Fu, Fabian Fleischer, Youngjoon Kim, HyungSeok Han, Cen Zhang, Brian Junekyu Lee, Hanqing Zhao, Taesoo Kim

Abstract

DARPA's AI Cyber Challenge (AIxCC) showed that cyber reasoning systems (CRSs) can go beyond vulnerability discovery to autonomously confirm and patch bugs: seven teams built such systems and open-sourced them after the competition. Yet all seven open-sourced CRSs remain largely unusable outside their original teams, each bound to the competition cloud infrastructure that no longer exists. We present OSS-CRS, an open, locally deployable framework for running and combining CRS techniques against real-world open-source projects, with budget-aware resource management. We ported the first-place system (Atlantis) and discovered 10 previously unknown bugs (three of high severity) across 8 OSS-Fuzz projects. OSS-CRS is publicly available.

Metadata

arXiv ID: 2603.08566
Provider: ARXIV
Primary Category: cs.CR
Published: 2026-03-09
Fetched: 2026-03-10 05:43

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.08566v1</id>\n    <title>OSS-CRS: Liberating AIxCC Cyber Reasoning Systems for Real-World Open-Source Security</title>\n    <updated>2026-03-09T16:26:33Z</updated>\n    <link href='https://arxiv.org/abs/2603.08566v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.08566v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>DARPA's AI Cyber Challenge (AIxCC) showed that cyber reasoning systems (CRSs) can go beyond vulnerability discovery to autonomously confirm and patch bugs: seven teams built such systems and open-sourced them after the competition. Yet all seven open-sourced CRSs remain largely unusable outside their original teams, each bound to the competition cloud infrastructure that no longer exists. We present OSS-CRS, an open, locally deployable framework for running and combining CRS techniques against real-world open-source projects, with budget-aware resource management. We ported the first-place system (Atlantis) and discovered 10 previously unknown bugs (three of high severity) across 8 OSS-Fuzz projects. OSS-CRS is publicly available.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.CR'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-09T16:26:33Z</published>\n    <arxiv:comment>Version 1.0 (March 2026), OSS-CRS: an open-source framework for porting, deploying, and composing AIxCC cyber reasoning systems. Project page: https://github.com/sslab-gatech/oss-crs</arxiv:comment>\n    <arxiv:primary_category term='cs.CR'/>\n    <author>\n      <name>Andrew Chin</name>\n    </author>\n    <author>\n      <name>Dongkwan Kim</name>\n    </author>\n    <author>\n      <name>Yu-Fu Fu</name>\n    </author>\n    <author>\n      <name>Fabian Fleischer</name>\n    </author>\n    <author>\n      <name>Youngjoon Kim</name>\n    </author>\n    <author>\n      <name>HyungSeok Han</name>\n    </author>\n    <author>\n      <name>Cen Zhang</name>\n    </author>\n    <author>\n      <name>Brian Junekyu Lee</name>\n    </author>\n    <author>\n      <name>Hanqing Zhao</name>\n    </author>\n    <author>\n      <name>Taesoo Kim</name>\n    </author>\n  </entry>"
}