A curated collection of adversarial attack and defense on graph data.
-
Updated
Nov 7, 2023 - Python
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"
Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]
[MICCAI 2023] Official code repository of paper titled "Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation" accepted in MICCAI 2023 conference.
A Simple Baseline Achieving Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1. Paper at: https://arxiv.org/abs/2503.10635
[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
SAGA: Spectral Adversarial Geometric Attack on 3D Meshes (ICCV 2023)
Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks
AAAI 2025: Autonomous LLM-enhanced adversarial attack for text-to-motion
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
[ISBI 2025] Official code repository of paper titled "On Frequency Domain Adversarial Vulnerabilities of Volumetric Medical Image Segmentation" accepted in ISBI 2025 conference.
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.
Add a description, image, and links to the adversarial-attack topic page so that developers can more easily learn about it.
To associate your repository with the adversarial-attack topic, visit your repo's landing page and select "manage topics."