CS Ph.D. student at UC Berkeley. Visiting Researcher at Meta FAIR. AI security. Prompt Injection Defense.
Pinned Loading
-
facebookresearch/SecAlign
facebookresearch/SecAlign PublicRepo for the research paper "SecAlign: Defending Against Prompt Injection with Preference Optimization"
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.


