Popular GitHub Repositories for Backdoor Attacks

Backdoors Framework for Deep Learning and Federated Learning. A light-weight tool to conduct your research on backdoors.

TrojanZoo provides a universal pytorch platform to conduct security researches (especially backdoor attacks/defenses) of image classification in deep learning.

Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to potentially execute offline remote code execution without running any actual code on the victim's machine or thwart LLM-based fraud/moderation systems.

The official implementation of the CCS'23 paper, Narcissus clean-label backdoor attack -- only takes THREE images to poison a face recognition dataset in a clean-label way and achieves a 99.89% attack success rate.

ICML 2022 code for "Neurotoxin: Durable Backdoors in Federated Learning" https://arxiv.org/abs/2206.10341

[ICCV 2023] Source code for our paper "Rickrolling the Artist: Injecting Invisible Backdoors into Text-Guided Image Generation Models".

[MICCAI 2024] Official code repository of paper titled "BAPLe: Backdoor Attacks on Medical Foundation Models using Prompt Learning" accepted in MICCAI 2024 conference.

Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''

Fast integration of backdoor attacks in machine learning and federated learning.

This repository provide the studies on the security of language models for code (CodeLMs).

[IJCAI 2024] Imperio is an LLM-powered backdoor attack. It allows the adversary to issue language-guided instructions to control the victim model's prediction for arbitrary targets.

Official repository for CVPR'23 paper: Detecting Backdoors in Pre-trained Encoders

The code of AAAI-21 paper titled "Defending against Backdoors in Federated Learning with Robust Learning Rate".

???Breaking long thought processes of o1-like LLMs, such as DeepSeek-R1, QwQ

Backdoor Stuff in AI/ ML domain

Implementations and demo of a regular Backdoor and a Latent backdoor attack on Deep Neural Networks.

Code for paper: PoisonPrompt: Backdoor Attack on Prompt-based Large Language Models, IEEE ICASSP 2024. Demo:http://124.220.228.133:11107

[NeurIPS 2021] Source code for the paper "Qu-ANTI-zation: Exploiting Neural Network Quantization for Achieving Adversarial Outcomes"

FedDefender is a novel defense mechanism designed to safeguard Federated Learning from the poisoning attacks (i.e., backdoor attacks).