Zeyang Sha

Zeyang Sha

Associate Professor at Nanjing University of Science and Technology

* indicates corresponding author

2026

The Reasoning Trap: How Enhancing LLM Reasoning Amplifies Tool Hallucination
Chenlong Yin, Zeyang Sha*, Shiwen Cui, Changhua Meng, Zechao Li ACL Main 2026
Teach to Reason Safely: Policy-Guided Safety Tuning for MLRMs
Jingyu Zhang, Kun Yang*, Ming Wen, Zhuoer Xu, Zeyang Sha*, Shiwen Cui, Zhaohui Yang ICLR 2026

2025

Single AI Agent Runtime Security Testing Standards
Ant Group WDTA 2025
AI智能体安全治理白皮书
China Telecom, MPS, Journal of Information Security Research Editorial Office, Huawei Group, Ant Group, Tsinghua University, Shanghai Jiao Tong University 中国电信
终端智能体安全2025
Shanghai Artificial Intelligence Laboratory, CAICT, Ant Group, IIFAA WAIC 2025

2024

Conversation Reconstruction Attack Against GPT Models
Junjie Chu, Zeyang Sha*, Michael Backes, Yang Zhang* EMNLP Main 2024
ZeroFake: Zero-Shot Detection of Fake Images Generated and Edited by Text-to-Image Generation Models
Zeyang Sha, Yicong Tan, Mingjie Li, Michael Backes, Yang Zhang CCS 2024
Games and Beyond: Analyzing the Bullet Chats of Esports Livestreaming
Yukun Jiang, Xinyue Shen, Rui Wen, Zeyang Sha, Junjie Chu, Yugeng Liu, Michael Backes, Yang Zhang ICWSM 2024

2023

DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Generation Models
Zeyang Sha, Zheng Li, Ning Yu, Yang Zhang CCS 2023 Best Paper Finalist · CSAW Europe 2024
Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders
Zeyang Sha, Xinlei He, Ning Yu, Michael Backes, Yang Zhang CVPR 2023