GPT-5.5 Bio Bug Bounty

GPT-5.5 Bio Bug Bounty

Details about the OpenAI Bio Bounty program

GPT-5.1-Codex-Max System Card

This system card outlines the comprehensive safety measures implemented for GPT‑5. 1-CodexMax.

Update to GPT-5 System Card: GPT-5.2

GPT-5. 2 is the latest model family in the GPT-5 series.

Expanding Daybreak as the Cyber Defense Window Narrows

Meet GPT-5. 6-Cyber, OpenAI’s cybersecurity-specific model available through Daybreak Red for authorized vulnerability research, exploit validation, and security testing.

Addendum to GPT-5 System Card: Sensitive conversations

This system card details GPT-5’s improvements in handling sensitive conversations, including new benchmarks for emotional reliance, mental health, and jailbreak resistance.

Beyond Attack Success Rate: Cost-Aware Metric for Evaluating Iterative LLM Jailbreaks

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.

Estimating worst case frontier risks of open weight LLMs

In this paper, we study the worst-case frontier risks of releasing gpt-oss. We introduce malicious fine-tuning (MFT), where we attempt to elicit maximum capabilities by fine-tuning gpt-oss to be as capable as possible in two domains: biology and cybersecurity.

AI Security Leaderboard: Methodology, Results and Minimal Standard

arXiv:2608. 03070v1 Announce Type: cross Abstract: Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much protection these safeguards provide, or how consistently across developers.

SEC-bench Pro: Can Language Models Solve Long-Horizon Software Security Tasks?

arXiv:2605. 26548v2 Announce Type: replace-cross Abstract: Finding a real vulnerability in complicated systems is a challenging, long-horizon task that demands reasoning across an entire codebase to produce a working proof-of-concept (PoC).

Previewing GPT-5.6 Sol: a next-generation model

OpenAI previews GPT-5. 6 Sol, a next-generation model with stronger capabilities in coding, science, and cybersecurity, paired with its most advanced safety stack.

GPT-5.5 System Card

gpt-oss-safeguard technical report

gpt-oss-safeguard-120b and gpt-oss-safeguard-20b are two open-weight reasoning models post-trained from the gpt-oss models and trained to reason from a provided policy in order to label content under that policy. In this report, we describe gpt-oss-safeguard’s capabilities and provide our baseline safety evaluations on the gpt-oss-safeguard models, using the underlying gpt-oss models as a baseline.