Showing 2026Show all
3 papers · 1 filter
cs.AI2026
DP-MIND: Differentially private memory-guided Long context Inference
Zhihao Liu, Yitian Cheng, Shuang Liu +3
LLM-as-a-Service has become a dominant paradigm for accessing large language models without requiring local deployment. However, the process raises severe privacy concerns when use…
cs.AI2026
Adaptive and Explicit safe: Triggering Latent Safety Awareness in Large Reasoning Models
Ke Miao, Jiaxin Li, Hongliang Chen +2
While Large Reasoning Models (LRMs) excel at complex tasks, they remain highly vulnerable to sophisticated jailbreaks and direct harmful queries. To address this vulnerability, pri…
cs.CV2026
JANUS: A Lightweight Framework for Jailbreaking Text-to-Image Models via Distribution Optimization
Haolun Zheng, Yu He, Tailun Chen +6
Text-to-image (T2I) models such as Stable Diffusion and DALLE remain susceptible to generating harmful or Not-Safe-For-Work (NSFW) content under jailbreak attacks despite deployed…