other
cybersecurity risk uplift
otheractive
cybersecurity-risk-uplift-2e7bb760·1 events·first seen 28d agoAliases: cybersecurity risk uplift
Co-occurring entities
More like this (12)
biology risk upliftcyberattack scaling lawTrusted Access for CyberCybersecurity Task Evaluationreward hackingAI Cybersecurity Threat Evaluation FrameworkOpenAI Cybersecurity Grant ProgramCyberSecEval 2US Cyber and AI Safety InstituteCyber Verification ProgramUAR (Unforeseen Attack Robustness)U.S. Cyber Command
Recent events (1)
Estimating Worst-Case Frontier Risks of Open-Weight LLMs
OpenAI introduces a methodology called malicious fine-tuning (MFT) to assess worst-case risks of releasing open-weight models, specifically applied to their internal model gpt-oss. The study attempts to elicit maximum dangerous capabilities in biology and cybersecurity domains through targeted fine-tuning. This represents a systematic effort to quantify uplift risks before open-weight releases, informing OpenAI's open-weight release policy.