collaborators

7 papers

cs.CR2026

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…

cs.CR2026

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…

cs.CV2025

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…

cs.CR2025

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…

cs.MA2025

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…

cs.CR2025

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…