Randomized Smoothing

Certified Robustness: Fundamentals and Challenges

Overview of classical and State-of-the-Art approaches to certify ML models’ robustness.

Jan 24, 2023 6:00 PM NTR LABS Webinars

Aleksandr Petiushko Александр Петюшко

Certified Robustness: Fundamentals and Challenges

Smoothed Embeddings for Certified Few-Shot Learning

Geometrical approach for certified few-shot learning via randomized smoothing of templates.

Mikhail Pautov, Olesya Kuznetsova, Nurislam Tursynbek, Aleksandr Petiushko Александр Петюшко, Ivan Oseledets

Certified Robustness via Randomized Smoothing over Multiplicative Parameters of Input Transformations

A novel method of certified robustness using Rayleigh dostribution for smoothing when transformations consist not additive but multiplicative group.

Nikita Muravev, Aleksandr Petiushko Александр Петюшко

Certified Robustness, High Dimensions and Computer Vision

Challenges of Certified Robustness in Computer Vision connected with high dimensionality.

Oct 29, 2021 12:00 AM SAMPLE

Aleksandr Petiushko Александр Петюшко

Certified Robustness in High Dimensions

The overview of certified robustness problems in high dimensions.

Apr 29, 2021 12:00 AM SkolTech

Aleksandr Petiushko Александр Петюшко

Certified Robustness in High Dimensions

Adversarial and Certified Robustness

Analysis of both empirical and theoretical approaches to study Adversarial Robustness (Adversarial Attacks, Certified Robustness)

Sep 20, 2020 12:00 AM ODS DataFest 2020

Aleksandr Petiushko Александр Петюшко

Adversarial and Certified Robustness

Certified Robustness for modern NN

The overview of certified robustness problems.

May 24, 2020 12:00 AM HSE/SkolTech, Statistical Learning Olympiad

Aleksandr Petiushko Александр Петюшко

Certified Robustness for modern NN