Topic: "backdoor-defense"
THUYimingLi/backdoor-learning-resources
A list of backdoor learning resources
Size: 1.07 MB - Last synced at: about 9 hours ago - Pushed at: 12 months ago - Stars: 1,112 - Forks: 173
penghui-yang/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A curated list of papers & resources linked to data poisoning, backdoor attacks and defenses against them (no longer maintained)
Size: 52.7 KB - Last synced at: 9 days ago - Pushed at: 7 months ago - Stars: 265 - Forks: 25
bboylyg/NAD
This is an implementation demo of the ICLR 2021 paper [Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks](https://openreview.net/pdf?id=9l0K4OM-oXE) in PyTorch.
Language: Python - Size: 3.77 MB - Last synced at: almost 2 years ago - Pushed at: over 3 years ago - Stars: 103 - Forks: 14
zihao-ai/Awesome-Backdoor-in-Deep-Learning
A curated list of papers & resources on backdoor attacks and defenses in deep learning.
Language: Python - Size: 1.95 MB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 73 - Forks: 7
wssun/TiSE-CodeLM-Security
This repository provide the studies on the security of language models for code (CodeLMs).
Language: Python - Size: 270 MB - Last synced at: about 1 month ago - Pushed at: 5 months ago - Stars: 48 - Forks: 3
csdongxian/ANP_backdoor
Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"
Language: Python - Size: 282 KB - Last synced at: over 1 year ago - Pushed at: about 2 years ago - Stars: 48 - Forks: 12
KaiyuanZh/FLIP
[ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
Language: Python - Size: 13.2 MB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 45 - Forks: 2
YiZeng623/I-BAU
Official Implementation of ICLR 2022 paper, ``Adversarial Unlearning of Backdoors via Implicit Hypergradient''
Language: Jupyter Notebook - Size: 11.9 MB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 31 - Forks: 11
mtuann/backdoor-ai-resources
Backdoor Stuff in AI/ ML domain
Size: 780 KB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 27 - Forks: 2
HanxunH/CognitiveDistillation
[ICLR2023] Distilling Cognitive Backdoor Patterns within an Image
Language: Python - Size: 1.58 MB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 27 - Forks: 2
Arya-f4/worldshellfinder
Web Shell finder using grep, where it has wordlist around the world to grep inside using regex and wordlist. So Lightweight and fast!
Language: Go - Size: 9.35 MB - Last synced at: 4 months ago - Pushed at: 6 months ago - Stars: 23 - Forks: 5
KaiyuanZh/OrthogLinearBackdoor
[IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks
Language: Python - Size: 50.8 MB - Last synced at: 4 months ago - Pushed at: 4 months ago - Stars: 21 - Forks: 2
BililiCode/ARGD
This is an implementation demo of the IJCAI 2022 paper [Eliminating Backdoor Triggers for Deep Neural Networks Using Attention Relation Graph Distillation](https://arxiv.org/abs/2204.09975) in PyTorch.
Language: Python - Size: 16.9 MB - Last synced at: 9 months ago - Pushed at: 9 months ago - Stars: 18 - Forks: 1
reds-lab/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.
Language: Python - Size: 115 KB - Last synced at: about 1 year ago - Pushed at: about 2 years ago - Stars: 14 - Forks: 0
Robin-WZQ/T2IShield
[ECCV'24] T2IShield: Defending Against Backdoors on Text-to-Image Diffusion Models
Language: Jupyter Notebook - Size: 4.52 MB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 13 - Forks: 2
Megum1/UNIT
[ECCV'24] UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
Language: Python - Size: 117 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 8 - Forks: 0
minliu01/non-adversarial_backdoor
Implementation of "Beating Backdoor Attack at Its Own Game" (ICCV-23).
Language: Python - Size: 624 KB - Last synced at: 4 months ago - Pushed at: over 1 year ago - Stars: 8 - Forks: 0
mtuann/research-papers
The resources are collected from various sources, including arXiv, NeurIPS, ICML, ICLR, ACL, EMNLP, AAAI, IJCAI, KDD, CVPR, ICCV, ECCV, NIPS, IEEE, ACM, Springer, ScienceDirect, Wiley, Nature, Science, and other top AI/ ML conferences and journals.
Size: 217 MB - Last synced at: 4 days ago - Pushed at: 4 days ago - Stars: 7 - Forks: 0
XuankunRong/BYE
Backdoor Cleaning without External Guidance in MLLM Fine-tuning
Language: Python - Size: 8.77 MB - Last synced at: 2 months ago - Pushed at: 2 months ago - Stars: 6 - Forks: 0
jeongjin0/detector-cleanse
An unofficial implementation of the detector cleanse introduced in the paper "BadDet: Backdoor Attacks on Object Detection."
Language: Python - Size: 366 KB - Last synced at: 7 months ago - Pushed at: 7 months ago - Stars: 6 - Forks: 0
LingyuDu/SecureGaze
The formal implementation for SenSys2025 paper: SecureGaze: Defending Gaze Estimation Against Backdoor Attacks
Language: Jupyter Notebook - Size: 51.2 MB - Last synced at: 22 days ago - Pushed at: 22 days ago - Stars: 5 - Forks: 0
Robin-WZQ/DAA
Dynamic Attention Analysis for Backdoor Detection in Text-to-Image Diffusion Models
Language: Python - Size: 21.4 MB - Last synced at: about 2 months ago - Pushed at: about 2 months ago - Stars: 5 - Forks: 1
lancopku/DAN
[Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
Language: Python - Size: 17.6 KB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 5 - Forks: 0
nazmul-karim170/NFT-Augmented-Backdoor-Purification
[ECCV'24] Official Implementation of "Augmented Neural Fine-Tuning for Efficient Backdoor Purification"
Language: Python - Size: 1.3 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 4 - Forks: 1
shawkui/Proactive_Defensive_Backdoor
Official implementation of the NeurIPS 24 paper "Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor"
Language: Python - Size: 29.2 MB - Last synced at: 5 months ago - Pushed at: 5 months ago - Stars: 3 - Forks: 0
seanpm2001/Doorcrete_Docs
🪨️🚪️📖️ The official documentation source repository for the Doorcrete project.
Language: Markdown - Size: 1.84 MB - Last synced at: 4 days ago - Pushed at: over 1 year ago - Stars: 3 - Forks: 1
HalilDeniz/BackDoorSim
BackdoorSim: An Educational into Remote Administration Tools
Language: Python - Size: 829 KB - Last synced at: over 1 year ago - Pushed at: over 1 year ago - Stars: 2 - Forks: 0
tsun/BDMAE
Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
Language: Python - Size: 13.1 MB - Last synced at: almost 2 years ago - Pushed at: almost 2 years ago - Stars: 2 - Forks: 0
seanpm2001/ARCHIVE_Doorcrete.github.io
🗄️🌐️ Archive of the former seanpm2001 site, Doorcrete.github.io
Language: HTML - Size: 1.54 MB - Last synced at: 4 days ago - Pushed at: 4 months ago - Stars: 1 - Forks: 0
shawkui/Shared_Adversarial_Unlearning
Official implementation of the NeurIPS 2023 paper titled "Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples"
Language: Jupyter Notebook - Size: 29.1 MB - Last synced at: 8 months ago - Pushed at: 8 months ago - Stars: 1 - Forks: 0
ASRS-Lab/Awesome-DL-Security-and-Privacy-Papers
Awesome-DL-Security-and-Privacy-Papers
Language: SCSS - Size: 105 KB - Last synced at: 10 days ago - Pushed at: 8 months ago - Stars: 1 - Forks: 0
nazmul-karim170/FIP-Fisher-Backdoor-Removal
[CCS'24] Official Implementation of "Fisher Information guided Purification against Backdoor Attacks"
Language: Python - Size: 1.19 MB - Last synced at: 11 months ago - Pushed at: 11 months ago - Stars: 1 - Forks: 1
um-dsp/PoisonSpot
Inspired by dynamic taint tracking, PoisonSpot uses fine-grained training provenance tracker that: (1) tags & traces the impact of every single training sample on model updates, (2) probabilistically scores suspect samples based on their linage of impact on model weights, and (3) separates the clean from the poisonous before retraining a model.
Language: Python - Size: 897 MB - Last synced at: 12 days ago - Pushed at: 12 days ago - Stars: 0 - Forks: 0
Pratyay-Ghosh/t2i
Generate images based on text prompts using Cloudflare's Workers AI. This is a modified worker that allows you to input custom prompts directly from the website, using the @cf/stabilityai/stable-diffusion-xl-base-1.0 model.
Language: TypeScript - Size: 68.4 KB - Last synced at: 3 months ago - Pushed at: 3 months ago - Stars: 0 - Forks: 0
liuyugeng/backdoor_detection
This is a project used for detecting backdoors at different levels.
Language: Python - Size: 76.2 KB - Last synced at: over 2 years ago - Pushed at: over 2 years ago - Stars: 0 - Forks: 1
