AI驱动的自动漏洞发现与修复系统，获DARPA人工智能网络安全挑战赛冠军
ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System
- 融合大模型与程序分析技术，实现跨语言漏洞检测
- 在多种代码库中实现高精度漏洞定位与语义正确修复
- 适合安全研究者与自动化攻防系统开发者参考
我们介绍ATLANTIS，由亚特兰大团队开发的网络推理系统，在2025年8月举行的DEF CON 33大会上荣获DARPA人工智能网络安全挑战赛（AIxCC）决赛一等奖。AIxCC（2023–2025）要求参赛队伍构建能够以现代软件的速度和规模自主发现并修补漏洞的智能系统。ATLANTIS将大语言模型（LLMs）与程序分析技术结合，整合符号执行、定向模糊测试和静态分析，克服了自动化漏洞发现与程序修复中的局限性。该系统由佐治亚理工学院、三星研究院、KAIST和POSTECH研究人员共同开发，解决了核心挑战：在从C到Java的多样化代码库中实现可扩展性，兼顾高精度与广泛覆盖，并生成保持原有行为意图的语义正确补丁。本文详述了ATLANTIS的设计理念、架构决策与实现策略，分享了在程序分析与现代AI结合推动自动化安全边界时的经验教训，并公开相关成果以支持复现与后续研究。
原文摘要 · Abstract (English)
We present ATLANTIS, the cyber reasoning system developed by Team Atlanta that won 1st place in the Final Competition of DARPA's AI Cyber Challenge (AIxCC) at DEF CON 33 (August 2025). AIxCC (2023-2025) challenged teams to build autonomous cyber reasoning systems capable of discovering and patching vulnerabilities at the speed and scale of modern software. ATLANTIS integrates large language models (LLMs) with program analysis -- combining symbolic execution, directed fuzzing, and static analysis -- to address limitations in automated vulnerability discovery and program repair. Developed by researchers at Georgia Institute of Technology, Samsung Research, KAIST, and POSTECH, the system addresses core challenges: scaling across diverse codebases from C to Java, achieving high precision while maintaining broad coverage, and producing semantically correct patches that preserve intended behavior. We detail the design philosophy, architectural decisions, and implementation strategies behind ATLANTIS, share lessons learned from pushing the boundaries of automated security when program analysis meets modern AI, and release artifacts to support reproducibility and future research.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。