The official implementation of A Unified Game-Theoretic Interpretation of Adversarial Robustness.

Overview

This repository is the official implementation of A Unified Game-Theoretic Interpretation of Adversarial Robustness.

Requirements

pip install -r requirements.txt

Pre-trained Models

We used the pre-trained models on the ImageNet dataset released by https://github.com/microsoft/robust-models-transfer.

Usage

Here, we take the untargeted PGD attack on the standard ResNet-18 as an example.

  1. Generate adversarial examples on the pre-trained model

    python gene_adv_imgs_untarget.py --root=<path_to_data> --dataset_name=imagenet --arch=resnet18 --std_model_path=<path_to_model>
  2. Sample variable pairs and contexts for the computation of interactions

    python gene_pairs.py --arch=resnet18 --ratios 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9
  3. Compute the model output on masked samples

    python m_order_interaction_logit.py --root=<path_to_data> --dataset_name=imagenet --arch=resnet18 --std_model_path=<path_to_model> --ratios 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9
  4. Compute interactions based on the model output

    python compute_interactions.py --root=<path_to_data> --dataset_name=imagenet --arch=resnet18 --std_model_path=<path_to_model> --ratios 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9
  5. Plot the average interaction in normal samples and adversarial examples, just like Figure 3 in the paper.

    python plot.py --arch=resnet --ratios 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9
    
You might also like...
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams
Adversarial Robustness Toolbox (ART) - Python Library for Machine Learning Security - Evasion, Poisoning, Extraction, Inference - Red and Blue Teams

Adversarial Robustness Toolbox (ART) is a Python library for Machine Learning Security. ART provides tools that enable developers and researchers to defend and evaluate Machine Learning models and applications against the adversarial threats of Evasion, Poisoning, Extraction, and Inference. ART supports all popular machine learning frameworks (TensorFlow, Keras, PyTorch, MXNet, scikit-learn, XGBoost, LightGBM, CatBoost, GPy, etc.), all data types (images, tables, audio, video, etc.) and machine learning tasks (classification, object detection, speech recognition, generation, certification, etc.).

Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness

Imbalanced Gradients: A Subtle Cause of Overestimated Adversarial Robustness Code for Paper "Imbalanced Gradients: A Subtle Cause of Overestimated Adv

Code repository accompanying the paper "On Adversarial Robustness: A Neural Architecture Search perspective"

On Adversarial Robustness: A Neural Architecture Search perspective Preparation: Clone the repository: https://github.com/tdchaitanya/nas-robustness.g

Hierarchical-Bayesian-Defense - Towards Adversarial Robustness of Bayesian Neural Network through Hierarchical Variational Inference (Openreview)
Official implementation of "Open-set Label Noise Can Improve Robustness Against Inherent Label Noise" (NeurIPS 2021)

Open-set Label Noise Can Improve Robustness Against Inherent Label Noise NeurIPS 2021: This repository is the official implementation of ODNL. Require

Official implementation of
Official implementation of "A Unified Objective for Novel Class Discovery", ICCV2021 (Oral)

A Unified Objective for Novel Class Discovery This is the official repository for the paper: A Unified Objective for Novel Class Discovery Enrico Fini

Official implementation of the paper:
Official implementation of the paper: "LDNet: Unified Listener Dependent Modeling in MOS Prediction for Synthetic Speech"

LDNet Author: Wen-Chin Huang (Nagoya University) Email: [email protected] This is the official implementation of the paper "LDNet

This is the official repository for evaluation on the NoW Benchmark Dataset. The goal of the NoW benchmark is to introduce a standard evaluation metric to measure the accuracy and robustness of 3D face reconstruction methods from a single image under variations in viewing angle, lighting, and common occlusions.
Owner
Jie Ren
Jie Ren
PyTorch Implementation of the SuRP algorithm by the authors of the AISTATS 2022 paper "An Information-Theoretic Justification for Model Pruning"

PyTorch Implementation of the SuRP algorithm by the authors of the AISTATS 2022 paper "An Information-Theoretic Justification for Model Pruning".

Berivan Isik 8 Dec 8, 2022
PyTorch implementation of our ICCV 2021 paper, Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents.

PyTorch implementation of our ICCV 2021 paper, Interpretation of Emergent Communication in Heterogeneous Collaborative Embodied Agents.

Saim Wani 4 May 8, 2022
Pytorch implementation for "Adversarial Robustness under Long-Tailed Distribution" (CVPR 2021 Oral)

Adversarial Long-Tail This repository contains the PyTorch implementation of the paper: Adversarial Robustness under Long-Tailed Distribution, CVPR 20

Tong WU 89 Dec 15, 2022
graph-theoretic framework for robust pairwise data association

CLIPPER: A Graph-Theoretic Framework for Robust Data Association Data association is a fundamental problem in robotics and autonomy. CLIPPER provides

MIT Aerospace Controls Laboratory 118 Dec 28, 2022
Information-Theoretic Multi-Objective Bayesian Optimization with Continuous Approximations

Information-Theoretic Multi-Objective Bayesian Optimization with Continuous Approximations Requirements The code is implemented in Python and requires

null 1 Nov 3, 2021
Interpretation of T cell states using reference single-cell atlases

Interpretation of T cell states using reference single-cell atlases ProjecTILs is a computational method to project scRNA-seq data into reference sing

Cancer Systems Immunology Lab 139 Jan 3, 2023
Consistency Regularization for Adversarial Robustness

Consistency Regularization for Adversarial Robustness Official PyTorch implementation of Consistency Regularization for Adversarial Robustness by Jiho

null 40 Dec 17, 2022
Multitask Learning Strengthens Adversarial Robustness

Multitask Learning Strengthens Adversarial Robustness

Columbia University 15 Jun 10, 2022
Implementations of orthogonal and semi-orthogonal convolutions in the Fourier domain with applications to adversarial robustness

Orthogonalizing Convolutional Layers with the Cayley Transform This repository contains implementations and source code to reproduce experiments for t

CMU Locus Lab 36 Dec 30, 2022
Improving adversarial robustness by a coupling rejection strategy

Adversarial Training with Rectified Rejection The code for the paper Adversarial Training with Rectified Rejection. Environment settings and libraries

Tianyu Pang 29 Jan 6, 2023