Songsci1024

OrderBkd

Backdoor attack in NLP

dataset-distillation-with-attention-labels

Implementation of "Dataset Distillation with Attention Labels for fine-tuning BERT" (accepted by ACL2023 main (short))

LMSanitator

awesome-data-poisoning-and-backdoor-attacks

A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them (no longer maintained)

DCT

HiddenKiller

Code and data of the ACL-IJCNLP 2021 paper "Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Trigger"

StyleAttack

Code and data of the EMNLP 2021 paper "Mind the Style of Text! Adversarial and Backdoor Attacks Based on Text Style Transfer"

Machine-Learning-Security-Seminar

Machine Learning & Security Seminar @Purdue University

bertviz

BertViz: Visualize Attention in NLP Models (BERT, GPT2, BART, etc.)

AttenTD

Codes for NAACL'22 "A Study of the Attention Abnormality in Trojaned BERTs", a textural Trojan Detector

OpenBackdoor

An open-source toolkit for textual backdoor attack and defense (NeurIPS 2022 D&B, Spotlight)

ASSET

This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms." ASSET achieves state-of-the-art reliability in detecting poisoned samples in end-to-end supervised learning/ self-supervised learning/ transfer learning.

Awesome-Backdoor-in-Deep-Learning

A curated list of papers & resources on backdoor attacks and defenses in deep learning.

ONION

Official implementation of the EMNLP 2021 paper "ONION: A Simple and Effective Defense Against Textual Backdoor Attacks"

BkdAtk-LWS

Code and data of the ACL 2021 paper "Turn the Combination Lock: Learnable Textual Backdoor Attacks via Word Substitution"

OpenAttack

An Open-Source Package for Textual Adversarial Attack.

BITE

Code and data for paper "BITE: Textual Backdoor Attacks with Iterative Trigger Injection"

Time_Series_Backdoor_Attack

SaTML'23 paper "Backdoor Attacks on Time Series: A Generative Approach" by Yujing Jiang, Xingjun Ma, Sarah Monazam Erfani, and James Bailey.

Narcissus

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.

chatgpt-on-wechat

基于大模型搭建的聊天机器人，同时支持 微信公众号、企业微信应用、飞书、钉钉 等接入，可选择GPT3.5/GPT-4o/GPT4.0/ Claude/文心一言/讯飞星火/通义千问/ Gemini/GLM-4/Claude/Kimi/LinkAI，能处理文本、语音和图片，访问操作系统和互联网，支持基于自有知识库进行定制企业智能客服。

DBD

BackdoorBox

The open-sourced Python toolbox for backdoor attacks and defenses.

Warping-based_Backdoor_Attack-release

WaNet - Imperceptible Warping-based Backdoor Attack (ICLR 2021)

input-aware-backdoor-attack-release

Input-aware Dynamic Backdoor Attack (NeurIPS 2020)

trojanzoo

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

Beatrix

Purifier

Purifier: Plug-and-play Backdoor Mitigation for Pre-trained Models Via Anomaly Activation Suppression

BackdoorBench

backdoor-learning-resources

A list of backdoor learning resources

CEF-SsL

Repository for the paper "SoK: The Impact of Unlabelled Data in Cyberthreat Detection", published at EuroSP2022.