EigenShield: Inference-Time, Model-Agnostic Jailbreaking Defense via Causal Subspace Filtering.
Nastaran Darabi, Devashri Naik, Sina Tayebati, Dinithi Jayasuriya, Ranganath Krishnan, Amit Ranjan Trivedi
Browse the full AAAI paper archive.
Nastaran Darabi, Devashri Naik, Sina Tayebati, Dinithi Jayasuriya, Ranganath Krishnan, Amit Ranjan Trivedi
Browse the full AAAI paper archive.