TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.
-
Updated
Oct 21, 2024 - Python
TransferAttack is a pytorch framework to boost the adversarial transferability for image classification.
Repository of paper "TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack" (ECAI'24)
Simple code related to adversarial examples, attacks, and defenses.
This github repository contains the official code for the papers, "Robustness Assessment for Adversarial Machine Learning: Problems, Solutions and a Survey of Current Neural Networks and Defenses" and "One Pixel Attack for Fooling Deep Neural Networks"
[MICCAI 2023] Official code repository of paper titled "Frequency Domain Adversarial Training for Robust Volumetric Medical Segmentation" accepted in MICCAI 2023 conference.
A curated collection of adversarial attack and defense on graph data.
[NeurIPS-2023] Annual Conference on Neural Information Processing Systems
SAGA: Spectral Adversarial Geometric Attack on 3D Meshes (ICCV 2023)
Set-level Guidance Attack: Boosting Adversarial Transferability of Vision-Language Pre-training Models. [ICCV 2023 Oral]
An adversarial image generator
Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networks
Gaussian process regression-based adversarial image detection
Compose desired image with data such that will cause pretrained models misbehave.
Jeu de la bataille navale en Python avec simulation d'un joueur adverse
[CVPR 2021] Official repository for "Prototype-supervised Adversarial Network for Targeted Attack of Deep Hashing"
[SIGIR 2021] Official repository for "Targeted Attack and Defense for Deep Hashing"
Code to generate and extend the TCAB dataset.
Official implementation of CVPR2020 Paper "Cooling-Shrinking Attack"
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."