Product

H-Node Attack and Defense in Large Language Models

@ericyocamby Eric Yocam · California Polytechnic State University

0

Identifies hallucination-linked internal nodes in LLMs, shows how they can be exploited, and introduces defenses against those attacks.

Built withPythonPyTorchHugging Face Transformersllmadversarial-attacksai-securityinterpretability

See what other members are building and what each project is looking for.