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
43.26/100
前 12.1%
全站排名 #7,819
发表论文4 篇
平均评分
年均产出4.0 篇/年
Edoardo Debenedetti
研究方向
machine learning · adversarial examples · evasion attacks
8
AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
ICML 2025Oral
二作33
Measuring Non-Adversarial Reproduction of Training Data in Large Language Models
ICLR 2025Poster
三作22
Adversarial Search Engine Optimization for Large Language Models
ICLR 2025Poster
二作21
AutoAdvExBench: Benchmarking Autonomous Exploitation of Adversarial Example Defenses
ICLR 2025Rejected
二作