Deep Learning

Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
Elegant way of measuring both aleatoric and epistemic uncertainties for neural nets.
Nikita Kotelevskii, Alexander Fishkov, Kirill Fedyanin, Aleksandr Petiushko Александр Петюшко, Maxim Panov
PDF Cite arXiv OpenReview Conf WorkshopWeb
Nonparametric Uncertainty Quantification for Single Deterministic Neural Network
Interviews in Deep Learning research with Aleksandr Petiushko
Fireside chat about ML/DL interviews.
Sep 3, 2021 12:00 AM DLS Podcasts
Aleksandr Petiushko Александр Петюшко
YT Podcast Google Podcasts Apple Podcasts Spotify Spotify for Podcasters Yandex Music In Russian
Interviews in Deep Learning research with Aleksandr Petiushko
Manifold Hypothesis in Data Analysis: Double Geometrically-Probabilistic Approach to Manifold Dimension Estimation
Elegant ways to check the so-called “Manifold Hypothesis” for FaceID using geoemtric (Ninkiwsky-based) and probabilistic approaches.
Alexander Ivanov, Gleb Nosovskiy, Alexey Chekunov, Denis Fedoseev, Vladislav Kibkalo, Mikhail Nikulin, Fedor Popelenskiy, Stepan Komkov, Ivan Mazurenko, Aleksandr Petiushko Александр Петюшко
PDF Cite DOI arXiv
Manifold Hypothesis in Data Analysis: Double Geometrically-Probabilistic Approach to Manifold Dimension Estimation
Darker than Black-Box: Face Reconstruction from Similarity Queries
Reconstruction of a face embedding using only similarity score from FaceID system.
Anton Razzhigaev, Klim Kireev, Igor Udovichenko, Aleksandr Petiushko Александр Петюшко
PDF Cite Code DOI arXiv
Darker than Black-Box: Face Reconstruction from Similarity Queries
MDMMT: Multidomain Multimodal Transformer for Video Retrieval
A State-of-the-Art Video Retrieval Method.
Maksim Dzabraev, Maksim Kalashnikov, Stepan Komkov, Aleksandr Petiushko Александр Петюшко
PDF Cite Code Slides Video Source Document DOI arXiv WorkshopWeb
MDMMT: Multidomain Multimodal Transformer for Video Retrieval
AdvHat: Real-World Adversarial Attack on ArcFace Face ID System
A practical approach to generate forehand printed patch to fool the best FaceID system - Arcface - in real world.
Stepan Komkov, Aleksandr Petiushko Александр Петюшко
PDF Cite Code Poster Slides Video Source Document DOI arXiv Demo
AdvHat: Real-World Adversarial Attack on ArcFace Face ID System
Robustness Threats of Differential Privacy
Surprising empirical observation showing how Differential Privacy hurts Adversarial Robustness.
Nurislam Tursynbek, Aleksandr Petiushko Александр Петюшко, Ivan Oseledets
PDF Cite arXiv Conf WorkshopWeb
Robustness Threats of Differential Privacy
Artificial Intelligence: Problems and Prospects
Fireside chat of the Mathematical Theory of Intelligent Systems chair about the Artificial Intelligence.
Valery Kudryavtsev, Vadim Kozlov, Aleksandr Ryzhov, Ivan Mazurenko, Grigory Bokov, Aleksandr Petiushko Александр Петюшко
PDF Cite Source Document In Russian
Artificial Intelligence: Problems and Prospects
Black-Box Face Recovery from Identity Features
Reconstruction of face using only similarity and norm of the embedding of a blac-box FaceID system.
Anton Razzhigaev, Klim Kireev, Edgar Kaziakhmedov, Nurislam Tursynbek, Aleksandr Petiushko Александр Петюшко
PDF Cite Code Slides Video Source Document DOI arXiv WorkshopWeb
Black-Box Face Recovery from Identity Features
On Adversarial Patches: Real-World Attack on ArcFace-100 Face Recognition System
Two versions of a real-world adversarial attack (nose patch and adversarial glasses) for a top FaceID system - Arcface.
Mikhail Pautov, Grigorii Melnikov, Edgar Kaziakhmedov, Klim Kireev, Aleksandr Petiushko Александр Петюшко
PDF Cite Source Document DOI arXiv
On Adversarial Patches: Real-World Attack on ArcFace-100 Face Recognition System