A curated collection of adversarial attack and defense on graph data.

TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.

[NeurIPS-2023] Annual Conference on Neural Information Processing Systems

Official implementation of CVPR2020 Paper "Cooling-Shrinking Attack"

[MICCAI 2023] Official code repository of paper titled "Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation" accepted in MICCAI 2023 conference.

Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]

[CVPR 2021] Official repository for "Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing"

[NeurIPS'20] Learning Black-Box Attackers with Transferable Priors and Query Feedback

Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks

SAGA: Spectral Adversarial Geometric Attack on 3D Meshes (ICCV 2023)

From Gradient Leakage to Adversarial Attacks in Federated Learning

Repository of paper "TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack" (ECAI'24)

vanilla training and adversarial training in PyTorch

GraphReach : Position-Aware Graph Neural Network using Reachability Estimations, IJCAI'21

Gaussian process regression-based adversarial image detection

Neural Network Adversarial Attack Method Based on Improved Genetic Algorithm

Compose desired image with data such that will cause pretrained models misbehave.

Code to generate and extend the TCAB dataset.

[SIGIR 2021] Official repository for "Targeted Attack and Defense for Deep Hashing"

[TMM 2022] Official repository for "Targeted Attack of Deep Hashing via Prototype-supervised Adversarial Networks"