Hanyu Zhu

This is Hanyu Zhu. I am a Ph.D. student in Computer Science at University of Massachusetts Dartmouth. I obtained my bachelor's degree from Sichuan University.

My current research interests mainly lie in security and privacy and trustworthy AI. In particular, I focus on (1) attack and defense of LLMs/MLLMs-empowered AI systems, and (2) vulnerabilities and trustworthiness of their real-world systems (e.g., integrated sensing and communications).

I am also interested in interdisciplinary areas related to AI and cybersecurity, such as AI4health and humanoid robotics.

I welcome opportunities for collaboration. Feel free to reach out to me. ✉️

[09/2025]      🎉 One paper has been accepted by NeurIPS 2025.

• Hanyu Zhu, Lance Fiondella, Jiawei Yuan, Kai Zeng, and Long Jiao. "NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge", the Thirty-Ninth Annual Conference on Neural Information Processing Systems (NeurIPS 2025). [paper]