Adversarial vulnerability of powerful near out-of-distribution detection

Overview

Adversarial vulnerability of powerful near out-of-distribution detection

by Stanislav Fort

In this repository we're collecting replications for the key experiments in the Adversarial vulnerability of powerful near out-of-distribution detection paper by Stanislav Fort.

The use of a large, pretrained and finetuned Vision Transformer for near-OOD detection on the CIFAR-100 vs CIFAR-10 task is demonstrated in this Colab. We showcase the use of the Standard Mahalanobis distance, the Relative Mahalanobis distance (presented in this paper), and the baseline Maximum of Softmax Probabilities. We show how to compute adversarial attacks on the 3 OOD metrics, and how the AUROC on the OOD task drops with the attack strength. The key result you will be able to replicate at the end of the Colab is the observation that Relative Mahalanobis distance is the most robust method out of the 3, followed by the standard Mahalanobis distance. The Max of Softmax Probabilities is the least robust to adversarial attacks.

The results you should expect from running the Colab in full (in around 45 minutes on a free GPU instance) are shown in bellow.

Colab: https://github.com/stanislavfort/adversaries_to_OOD_detection/blob/main/adversaries_to_strong_OOD_detectors.ipynb

Loss of AUROC on CIFAR-100 vs CIFAR-10 with adversarial perturbation strength:

An example of a source image, its magnified perturbation, and the resulting perturbed image:

The change of the Mahalanobis distance OOD score for 64 test images vs their perturbation strength:

Owner
Stanislav Fort
PhD student at Stanford | ML, AI & Physics
Stanislav Fort
Tianshou - An elegant PyTorch deep reinforcement learning library.

Tianshou (天授) is a reinforcement learning platform based on pure PyTorch. Unlike existing reinforcement learning libraries, which are mainly based on

Tsinghua Machine Learning Group 5.5k Jan 05, 2023
[CVPR 2022] Official Pytorch code for OW-DETR: Open-world Detection Transformer

OW-DETR: Open-world Detection Transformer (CVPR 2022) [Paper] Akshita Gupta*, Sanath Narayan*, K J Joseph, Salman Khan, Fahad Shahbaz Khan, Mubarak Sh

Akshita Gupta 127 Dec 27, 2022
TOOD: Task-aligned One-stage Object Detection, ICCV2021 Oral

One-stage object detection is commonly implemented by optimizing two sub-tasks: object classification and localization, using heads with two parallel branches, which might lead to a certain level of

264 Jan 09, 2023
A list of multi-task learning papers and projects.

This page contains a list of papers on multi-task learning for computer vision. Please create a pull request if you wish to add anything. If you are interested, consider reading our recent survey pap

svandenh 297 Dec 17, 2022
AirCode: A Robust Object Encoding Method

AirCode This repo contains source codes for the arXiv preprint "AirCode: A Robust Object Encoding Method" Demo Object matching comparison when the obj

Chen Wang 30 Dec 09, 2022
Making a music video with Wav2CLIP and VQGAN-CLIP

music2video Overview A repo for making a music video with Wav2CLIP and VQGAN-CLIP. The base code was derived from VQGAN-CLIP The CLIP embedding for au

Joel Jang | 장요엘 163 Dec 26, 2022
Pytorch implementation for "Implicit Semantic Response Alignment for Partial Domain Adaptation"

Implicit-Semantic-Response-Alignment Pytorch implementation for "Implicit Semantic Response Alignment for Partial Domain Adaptation" Prerequisites pyt

4 Dec 19, 2022
Lama-cleaner: Image inpainting tool powered by LaMa

Lama-cleaner: Image inpainting tool powered by LaMa

Qing 5.8k Jan 05, 2023
Welcome to The Eigensolver Quantum School, a quantum computing crash course designed by students for students.

TEQS Welcome to The Eigensolver Quantum School, a crash course designed by students for students. The aim of this program is to take someone who has n

The Eigensolvers 53 May 18, 2022
Release of the ConditionalQA dataset

ConditionalQA Datasets accompanying the paper ConditionalQA: A Complex Reading Comprehension Dataset with Conditional Answers. Disclaimer This dataset

14 Oct 17, 2022
🔥🔥High-Performance Face Recognition Library on PaddlePaddle & PyTorch🔥🔥

face.evoLVe: High-Performance Face Recognition Library based on PaddlePaddle & PyTorch Evolve to be more comprehensive, effective and efficient for fa

Zhao Jian 3.1k Jan 02, 2023
Metrics to evaluate quality and efficacy of synthetic datasets.

An Open Source Project from the Data to AI Lab, at MIT Metrics for Synthetic Data Generation Projects Website: https://sdv.dev Documentation: https://

The Synthetic Data Vault Project 129 Jan 03, 2023
[NeurIPS 2021] Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects

[NeurIPS 2021] Shape from Blur: Recovering Textured 3D Shape and Motion of Fast Moving Objects YouTube | arXiv Prerequisites Kaolin is available here:

Denys Rozumnyi 107 Dec 26, 2022
Self-training for Few-shot Transfer Across Extreme Task Differences

Self-training for Few-shot Transfer Across Extreme Task Differences (STARTUP) Introduction This repo contains the official implementation of the follo

Cheng Perng Phoo 33 Oct 31, 2022
Domain Generalization with MixStyle, ICLR'21.

MixStyle This repo contains the code of our ICLR'21 paper, "Domain Generalization with MixStyle". The OpenReview link is https://openreview.net/forum?

Kaiyang 208 Dec 28, 2022
A Multi-modal Model Chinese Spell Checker Released on ACL2021.

ReaLiSe ReaLiSe is a multi-modal Chinese spell checking model. This the office code for the paper Read, Listen, and See: Leveraging Multimodal Informa

DaDa 106 Dec 29, 2022
Learning to Self-Train for Semi-Supervised Few-Shot

Learning to Self-Train for Semi-Supervised Few-Shot Classification This repository contains the TensorFlow implementation for NeurIPS 2019 Paper "Lear

86 Dec 29, 2022
Differentiable Surface Triangulation

Differentiable Surface Triangulation This is our implementation of the paper Differentiable Surface Triangulation that enables optimization for any pe

61 Dec 07, 2022
Diverse Image Captioning with Context-Object Split Latent Spaces (NeurIPS 2020)

Diverse Image Captioning with Context-Object Split Latent Spaces This repository is the PyTorch implementation of the paper: Diverse Image Captioning

Visual Inference Lab @TU Darmstadt 34 Nov 21, 2022
MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation

MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation This repo is the official implementation of "MHFormer: Multi-Hypothesis Transforme

Vegetabird 281 Jan 07, 2023