News
Publications
Labs
Events
Jobs
Donate
About
Team
Newsletter
SAIF
Transparency
Privacy Policy
Terms of Service
Contact Us
Brendan Murphy
Latest
Illusory Safety: Redteaming DeepSeek R1 and the Strongest Fine-Tunable Models of OpenAI, Anthropic, and Google
GPT-4o Guardrails Gone: Data Poisoning & Jailbreak-Tuning
Data Poisoning in LLMs: Jailbreak-Tuning and Scaling Laws
Cite
×