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
46.85/100
前 10%
全站排名 #6,413
发表论文9 篇
平均评分
年均产出4.5 篇/年
Shengshan Hu
研究方向
Adversarial attack · machine learning · Privacy Protection · Federated learning · security
19
Vanish into Thin Air: Cross-prompt Universal Adversarial Attacks for SAM2
NeurIPS 2025Spotlight
24
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
NeurIPS 2025Poster
24
AdvEDM: Fine-grained Adversarial Attack against VLM-based Embodied Agents
NeurIPS 2025Poster
41
BadRobot: Jailbreaking Embodied LLM Agents in the Physical World
ICLR 2025Poster
27
MARS: A Malignity-Aware Backdoor Defense in Federated Learning
ICLR 2025Rejected
41
WISDOM: Progressive Curriculum Synthesis Makes LLMs Better Mathematical Reasoner
ICLR 2025Rejected