@OpenAINewsroom: The UK AI Security Institute (AISI) has published new research on “Boundary Point Jailbreaking” (BPJ...
The UK AI Security Institute (AISI) has published new research on “Boundary Point Jailbreaking” (BPJ) — a method for developing universal jailbreaks against system safeguards. We’ve deployed mitigations addressing jailbreaks uncovered through this BPJ research and further strengthened our systems to reduce susceptibility to this class of attack. We’re grateful for our continued collaboration with UK AISI and other external research and standards bodies to surface potential risks early. We’ll continue working closely together to advance AI safety and security. https://t.co/eJ1iiECAo9