In plain words: ATLANTIS pairs AI language models with classic bug-hunting tools that explore code paths, randomly test programs, and inspect source, so it can find and fix security holes on its own. It took first place in DARPA's AI Cyber Challenge final.
Abstract · ATLANTIS: AI-driven Threat Localization, Analysis, and Triage Intelligence System
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.
Taesoo Kim, HyungSeok Han, Soyeon Park, Dae R. Jeong, Dohyeok Kim, Dongkwan Kim, Eunsoo Kim, Jiho Kim, Joshua Wang, Kangsu Kim, Sangwoo Ji, Woosun Song, et al.
arXiv:2509.14589 · cs.CR, cs.AI · submitted Sep 18, 2025
abstract · pdf · Version 1.0 (September 17, 2025). Technical Report. Team Atlanta -- 1st place in DARPA AIxCC Final Competition. Project page: https://team-atlanta.github.io/