4 papers · 1 filter
Alignment Is Local: A Paired Diagnostic for GUI Agents under User-Side Persuasion
Haoxin An, Yunpeng Song, Zihao Bai +6
Trustworthy deployment of GUI agents in ubiquitous computing settings requires alignment that survives dynamic interaction and precise threat conditions, not just single-turn refus…
When Safe Concepts Become Unsafe: Multi-Concept Compositional Vulnerabilities in Text-to-Image Models
Chaoshuo Zhang, Yibo Liang, Mengke Tian +7
Text-to-image (T2I) models are increasingly optimized for following user instructions faithfully. However, we find that this capability introduces a safety vulnerability we call Mu…
GEO-Detective: Unveiling Location Privacy Risks in Images with LLM Agents
Xinyu Zhang, Yixin Wu, Boyang Zhang +4
Images shared on social media often expose geographic cues. While early geolocation methods required expert effort and lacked generalization, the rise of Large Vision Language Mode…
JADES: A Universal Framework for Jailbreak Assessment via Decompositional Scoring
Junjie Chu, Mingjie Li, Ziqing Yang +6
Accurately determining whether a jailbreak attempt has succeeded is a fundamental yet unresolved challenge. Existing evaluation methods rely on misaligned proxy indicators or naive…