Skip to content

EigenShield: Inference-Time, Model-Agnostic Jailbreaking Defense via Causal Subspace Filtering.

Nastaran Darabi, Devashri Naik, Sina Tayebati, Dinithi Jayasuriya, Ranganath Krishnan, Amit Ranjan Trivedi

VenueA*AAAI
Year2026
ProceedingsAAAI

Browse the full AAAI paper archive.