影响力指数
论文质量、代表作、近期表现、广度与样本量置信度综合计算
28.57/100
前 26.1%
全站排名 #16,783
发表论文9 篇
平均评分
年均产出3.0 篇/年
Tianhang Zheng
Assistant Professor@The State Key Laboratory of Blockchain and Data Security, Zhejiang University·中国·OpenReview
研究方向
Adversarial Machine Learning · Large Language Models · Jailbreaking Attacks and Defenses · Large Vision Models
21
Attack-Resistant Watermarking for AIGC Image Forensics via Diffusion-based Semantic Deflection
ICLR 2026Poster
20
TISR: Breaking Vision–Language Models via Text–Image Segmentation and Reassembly
ICLR 2026Withdrawn
11
Untargeted Jailbreak Attack
ICLR 2026Withdrawn
三作16
Dynamic Target Attack
ICLR 2026Rejected
三作10
Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
ICLR 2026Desk Rejected
5
Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services
ICLR 2026Withdrawn