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
61.71/100
前 4.4%
全站排名 #2,823
发表论文10 篇
平均评分
年均产出3.3 篇/年
Nils Lukas
研究方向
Security and Privacy · Machine Learning · Confidential Computing
27
DP-Fusion: Token-Level Differentially Private Inference for Large Language Models
ICLR 2026Poster
通讯19
Mitigating Watermark Forgery in Generative Models via Randomized Key Selection
ICLR 2026Rejected
通讯5
Collaborative Threshold Watermarking
ICLR 2026Withdrawn
三作-1
Open Models Can Silently Undermine Privacy: Context Inference Attacks without Jailbreaks
ICLR 2026Withdrawn
三作20
Mask Image Watermarking
NeurIPS 2025Poster
16
Optimizing Adaptive Attacks against Watermarks for Language Models
ICML 2025Spotlight
三作30
Optimizing Adaptive Attacks against Content Watermarks for Language Models
ICLR 2025Rejected
三作13
Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
ICML 2025Poster