影响力指数

28.56/100

前 26.1%

全站排名 #16,796

发表论文3 篇

平均评分5.4

年均产出1.5 篇/年

Lukas Struppek

Researcher@FAR.AI·美国·OpenReview

研究方向

Security and privacy in machine learning · AI safety · Trustworthy AI

Finding Dori: Memorization in Text-to-Image Diffusion Models Is Not Local

ICLR 2026Rejected

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks

ICLR 2024Poster

Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models

NeurIPS 2024Poster

合作者 (5)

Dominik Hintersdorf

Kristian Kersting

博士导师3 篇

Franziska Boenisch

Antoni Kowalczuk