影响力指数

-/100

发表论文3 篇

平均评分3.5

年均产出1.5 篇/年

Mikhail Pautov

Principal Researcher@AXXX·俄罗斯·OpenReview

研究方向

ai privacy · probability · certified robustness

ActiveMark: on watermarking of visual foundation models via massive activations

ICLR 2026Withdrawn

Spread them Apart: Towards Robust Watermarking of Generated Content

ICLR 2025Withdrawn

Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples

ICLR 2025Desk Rejected

合作者 (8)

Andrey V. Galichin

博士导师1 篇

Andrew Perminov

Kirill Lukyanov

Anna Chistyakova