Explore the GPT-5. 5 Bio Bug Bounty: a red-teaming challenge to find universal jailbreaks for bio safety risks, with rewards up to $25,000.
Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at OpenAI Blog.
Details about the OpenAI Bio Bounty program
This system card outlines the comprehensive safety measures implemented for GPT‑5. 1-CodexMax.
GPT-5. 2 is the latest model family in the GPT-5 series.
Meet GPT-5. 6-Cyber, OpenAI’s cybersecurity-specific model available through Daybreak Red for authorized vulnerability research, exploit validation, and security testing.
This system card details GPT-5’s improvements in handling sensitive conversations, including new benchmarks for emotional reliance, mental health, and jailbreak resistance.
The paper introduces a new metric, ASR_STEP, that extends the traditional attack success rate (ASR) by penalizing repeated calls to a victim large language model during jailbreak attempts. Experiments on JailBreakBench show that GCG’s scores drop by 7.0–8.7 percentage points after discounting, while PAP’s scores remain unchanged, and PAIR’s discount ranges from 3.4–12 percentage points depending on the iterative strategy. The authors argue that reporting both ASR and ASR_STEP makes the cost of repeated victim-model interactions explicit.