CV

Education

• Ph.D. student, Fudan University and Shanghai Innovation Institute, 2024-present

Research interests

• AI Security
• AI Safety
• Agent Safety
• RAG Security

Publications

Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction

Changyue Jiang et al. (2026). "Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction." ICML 2026.

MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning

Changyue Jiang et al. (2026). "MATE: Policy-Aware Security Auditing for Mobile Agents via Synthesis-Driven Trajectory Learning." USENIX Security 2026.

MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction

Changyue Jiang et al. (2026). "MirrorGuard: Toward Secure Computer-Use Agents via Simulation-to-Real Reasoning Correction." ACM CCS 2026.

Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications

Changyue Jiang et al. (2024). "Feedback-Guided Extraction of Knowledge Base from Retrieval-Augmented LLM Applications." arXiv preprint.