Peer Pressure: Execution-Verified Co-Evolution of Attacker and Defender Populations for Code Security↗ (원문, 새 창)

본문 미리보기

arXiv:2610.24896v1 Announce Type: new Abstract: LLM code agents increasingly ship code with little oversight, yet defenders trained on static vulnerability datasets fall behind adapting adversaries. We co-train attacker and defender instead, and let execution decide every reward: an attacker (Red) edits a real repository and earns nothing unless its patch applies, builds, passes the tests, completes its development task and reproduces a real exploit in an isolated container, whose path also lab