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
36.15/100
前 17.7%
全站排名 #11,383
发表论文11 篇
平均评分
年均产出3.7 篇/年
Guanlin Li
研究方向
Backdoor Attack · Watermark and Fingerprint · Adversarial Defense · Adversarial Attack
23
Image Can Bring Your Memory Back: A Novel Multi-Modal Guided Attack against Image Generation Model Unlearning
ICLR 2026Poster
二作6
Picky LLMs and Unreliable RMs: An Empirical Study on Safety Alignment after Instruction Tuning
ICLR 2026Rejected
一作10
Warfare: Breaking the Watermark Protection of AI-Generated Content
ICLR 2026Rejected
一作