most citedJBShield: Defending Large Language Models from Jailbreak Attacks through Activated Concept Analysis and Manipulation

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2026

VOID: Defeating Unauthorized Mimicry in Latent Diffusion Models

Chunlin Qiu, Ang Li, Tianxiao Huang +7

While Latent Diffusion Models (LDMs) have revolutionized visual synthesis, they are increasingly exploited for unauthorized mimicry of individuals. Existing defenses inject decepti…