6 citations · 7 across the 8 of their papers we have counts for
Showing 2026 · cs.CRShow all
2 papers · 2 filters
cs.CR2026
TooBad: Backdoor Diffusion Models with Ultra-Low Poison Rate and Imperceptible Trigger
Vu Tuan Truong, Long Bao Le
Diffusion models (DMs), despite their impressive capabilities across a wide range of generative tasks, have been shown to be vulnerable to backdoor attacks. However, existing backd…
cs.CR2026
Critical-CoT: A Robust Defense Framework against Reasoning-Level Backdoor Attacks in Large Language Models
Vu Tuan Truong, Long Bao Le
Large Language Models (LLMs), despite their impressive capabilities across domains, have been shown to be vulnerable to backdoor attacks. Prior backdoor strategies predominantly op…