7 papers
Your Agentic LLMs Secretly Encode Latent Signals of Indirect Prompt-Injection Exposure
Jianshuo Dong, Yiming Liu, Maosen Zhang +6
Agentic LLMs are vulnerable to indirect prompt injection (IPI) attacks, e.g., malicious side-tasks hidden in external tool results. While many efforts have sought to address the th…
State-Dependent Safety Failures in Multi-Turn Language Model Interaction
Pengcheng Li, Jie Zhang, Tianwei Zhang +5
Safety alignment in large language models is typically evaluated under isolated queries, yet real-world use is inherently multi-turn. Although multi-turn jailbreaks are empirically…
Visible Yet Unreadable: A Systematic Blind Spot of Vision Language Models Across Writing Systems
Jie Zhang, Ting Xu, Gelei Deng +5
Writing is a universal cultural technology that reuses vision for symbolic communication. Humans display striking resilience: we readily recognize words even when characters are fr…
IRCopilot: Automated Incident Response with Large Language Models
Xihuan Lin, Jie Zhang, Gelei Deng +4
Incident response plays a pivotal role in mitigating the impact of cyber attacks. In recent years, the intensity and complexity of global cyber threats have grown significantly, ma…
Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
Yutong Wu, Jie Zhang, Yiming Li +4
Vision Language Model (VLM)-based agents are stateful, autonomous entities capable of perceiving and interacting with their environments through vision and language. Multi-agent sy…
PoseGuard: Pose-Guided Generation with Safety Guardrails
Kongxin Wang, Jie Zhang, Peigui Qi +3
Pose-guided video generation has become a powerful tool in creative industries, exemplified by frameworks like Animate Anyone. However, conditioning generation on specific poses in…