2 papers
cs.AI2026
Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification
Md. Hasib Ur Rahman
Safety alignment in Large Language Models (LLMs) is often superficial, relying on refusal mechanisms that trigger only at the final stages of generation without erasing the foundat…
cs.SD2026
Voice Privacy from an Attribute-based Perspective
Mehtab Ur Rahman, Martha Larson, Cristian Tejedor-Garcia
Voice privacy approaches that preserve the anonymity of speakers modify speech in an attempt to break the link with the true identity of the speaker. Current benchmarks measure spe…