🪪About Me

I’m Shuo Shao😄, a fourth-year Ph.D. candidate with the State Key Laboratory of Blockchain and Data Security, Zhejiang University. I am hornord to be advised by Prof. Zhan Qin and Prof. Kui Ren. I also work closely with Dr. Yiming Li and Prof. Wenyuan Yang. I received my B.Eng. degree in Computer Science and Technology from Central South University in 2022, advised by Prof. Xiyao Liu.

My research interests primarily focus on Trustworthy AI. My previous work mainly addresses AI Copyright and Security, especially LLM Copyright Auditing via Watermarking and Fingerprinting, Backdoor Attack and Defense, and Privacy Extraction Attack and Defense. Currently, I am more focused on LLM and Agent Safety, particularly in the areas of Safety Alignment and Red-teaming.

---

🔥News

• [2026.3]: 🎉Our paper about Prompt Copyright Auditing is accepted by S&P 2026!
• [2026.2]: 🎉Our paper about T2I Jailbreak Attack is accepted by CVPR 2026!
• [2026.1]: 🎉Our paper about Black-box LLM Fingerprinting, entitled “Reading Between the Lines: Towards Reliable Black-box LLM Fingerprinting via Zeroth-order Gradient Estimation”, is accepted by WWW 2026!
• [2025.11]: 🎉Our paper about KV-cache Privacy Leakage and Defense is accepted by NDSS 2026!
• [2025.11]: 🎉Our paper about Markovian adaptive jailbreak attack is accepted by AAAI 2026!
• [2025.1]: 🎉Our paper about backdoor defense based on model reprogramming is accepted by ICLR 2025!
• [2024.8]: 🎉Our paper about model watermarking, entitled “Explanation as a Watermark: Towards Harmless and Multi-bit Model Ownership Verification via Watermarking Feature Attribution”, is accepted by NDSS 2025!
• [2024.4]: 🎉Our paper “FedTracker: Furnishing Ownership Verification and Traceability for Federated Learning Model” is accepted by TDSC!

---

✉️Contact

If you have any questions about my works, please feel free to contact me.

• Email: shaoshuo_ss@zju.edu.cn; shaoshuo2000@gmail.com