Popular GitHub Repositories for Defense

A pytorch adversarial library for attack and defense methods on images and graphs

Adversarial attacks and defenses on Graph Neural Networks.

Implementation of the KDD 2020 paper "Graph Structure Learning for Robust Graph Neural Networks"

A certifiable defense against adversarial examples by training neural networks to be provably robust

A survey on harmful fine-tuning attack for large language model

This repository contains the implementation of three adversarial example attack methods FGSM, IFGSM, MI-FGSM and one Distillation as defense against all attacks using MNIST dataset.

:skull: A collection of methods to fool the deep neural network :skull:

Feature Scattering Adversarial Training (NeurIPS19)

This is the official pytorch implementation for paper: IF-Defense: 3D Adversarial Point Cloud Defense via Implicit Function based Restoration

[ICML 2019] ME-Net: Towards Effective Adversarial Robustness with Matrix Estimation

This is the official code for the paper "Virus: Harmful Fine-tuning Attack for Large Language Models Bypassing Guardrail Moderation"

EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examples

Repo for papers to read on adversarial attack and defense techniques in the audio domain.

A Survey of Poisoning Attacks and Defenses in Recommender Systems

DiffusionGuard: A Robust Defense Against Malicious Diffusion-based Image Editing (ICLR 2025)

A Simple and Effective Solution For AISafety CVPR2022, ranked 5th

official Pytorch implementation of paper 'Improving transferability of 3D adversarial attacks with scale and shear transformations', Information Sciences, 2024

In this work the proposed defense strategy is evaluated against two black-box adversarial attacks, Hop Skip Jump and Square

we present an evaluation framework, named Visual Adversarial Recommender (\var), to empirically investigate the performance of defended or undefended DNNs in various visually-aware item recommendation tasks.

Adversarial Attacks and Defenses via Image perturbations