Paul Gavrikov's Projects
Unofficial implementation of the DeepMind papers "Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examples" & "Fixing Data Augmentation to Improve Adversarial Robustness" in PyTorch
Official implementation of Don't Look into the Sun: Adversarial Solarization Attacks on Image Classifiers
Official repository for the CVPRW2023 paper "An Extended Study of Human-like Behavior under Adversarial Training".
Bruteforce attack on Android Voice assistants to issue commands like phone calls with a zero permission app. This is an audible variant of the bruteforce attack describe in this publication: https://dl.acm.org/citation.cfm?id=3134052
:sunglasses: A curated list of awesome MLOps tools
Official code for the CVPR 2024 Paper "Can Biases in ImageNet Models Explain Generalization?".
A database of over 1.4 billion 3x3 convolution filters extracted from hundreds of diverse CNN models with relevant meta information (CVPR 2022 ORAL)
Code release for ConvNeXt model
Official repository of our submission "Adversarial Robustness through the Lens of Convolutional Filters" for the CVPR2022 Workshop "The Art of Robustness: Devil and Angel in Adversarial Machine Learning Workshop"
Implementation of Denoising Diffusion Probabilistic Model in Pytorch
This is an unofficial implementation of the diffusion-style noise frontend in "Intriguing properties of generative classifiers" by Priyank Jaini, Kevin Clark, Robert Geirhos to improve the shape-bias of vision models.
ImageBind One Embedding Space to Bind Them All
[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Official home of the jmDNS library
Keuper Labs website
Computer Vision and Robotics Library for AI
MEAL V2: Boosting Vanilla ResNet-50 to 80%+ Top-1 Accuracy on ImageNet without Tricks
Benchmark your model on out-of-distribution datasets with carefully collected human comparison data (NeurIPS 2021 Oral)
Official repository for the ICCVW2023 paper "On the Interplay of Convolutional Padding and Adversarial Robustness".