Jinyuan Liu 刘金源

USENIX Security 2026

Robust Watermarks Meet Backdoored Models: Evading Diffusion Semantic Watermarks via Stealthy Backdoor

Jinyuan Liu, Tianshuo Cong, Pei Li, Tianrui Wang, Xinlei He, Anyu Wang, and Xiaoyun Wang

Proceedings of the 35th USENIX Security Symposium (USENIX Security 26), 2026.

USENIX Security 2026

Cryptanalysis of LDPC-Based Pseudorandom Error-Correcting Codes

Tianrui Wang, Anyu Wang, Tianshuo Cong, Delong Ran, Jinyuan Liu, Xiaoyun Wang

KDD 2026 · Research Track

Rethinking the Stealthiness of Cryptographically Undetectable Backdoors in Practical RFF Learning

Tianshuo Cong, Pei Li, Haojie Wu, Jinyuan Liu, Tairong Huang, Guoyan Zhang, and Anyu Wang

The 32nd SIGKDD Conference on Knowledge Discovery and Data Mining, August 9–13, 2026, Jeju, Korea.

NDSS 2025 Poster

JailbreakEval: An Integrated Toolkit for Evaluating Jailbreak Attempts Against Large Language Models

Delong Ran, Jinyuan Liu, Yichen Gong, Jingyi Zheng, Xinlei He, Tianshuo Cong, Anyu Wang

Presented as an NDSS Symposium 2025 poster and awarded Best Technical Poster.

AAAI 2025

FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts

Yichen Gong, Delong Ran, Jinyuan Liu, Conglei Wang, Tianshuo Cong, Anyu Wang, Sisi Duan, Xiaoyun Wang

Proceedings of the AAAI Conference on Artificial Intelligence, 39(22): 23951–23959, 2025.

CCS-LAMPS 2024

Have You Merged My Model? On the Robustness of Large Language Model IP Protection Methods Against Model Merging

Tianshuo Cong, Delong Ran, Zesen Liu, Xinlei He, Jinyuan Liu, Yichen Gong, Qi Li, Anyu Wang, Xiaoyun Wang

Proceedings of the 1st ACM Workshop on Large AI Systems and Models with Privacy and Safety Analysis, 2024. Best Paper Award.