A curated list of papers & resources on backdoor attacks and defenses in deep learning.
-
Updated
Mar 15, 2024 - Python
A curated list of papers & resources on backdoor attacks and defenses in deep learning.
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.
BackdoorSim: An Educational into Remote Administration Tools
Codes for NeurIPS 2021 paper "Adversarial Neuron Pruning Purifies Backdoored Deep Models"
Fast integration of backdoor attacks in machine learning and federated learning.
[ICLR 2023, Best Paper Award at ECCV’22 AROW Workshop] FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning
This repository provide the studies on the security of language models for code (CodeLMs).
[ICLR2023] Distilling Cognitive Backdoor Patterns within an Image
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.
[IEEE S&P 2024] Exploring the Orthogonality and Linearity of Backdoor Attacks
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.
[Findings of EMNLP 2022] Expose Backdoors on the Way: A Feature-Based Efficient Defense against Textual Backdoor Attacks
Implementation of "Beating Backdoor Attack at Its Own Game" (ICCV-23).
[ECCV'24] UNIT: Backdoor Mitigation via Automated Neural Distribution Tightening
[ECCV'24] Official Implementation of "Augmented Neural Fine-Tuning for Efficient Backdoor Purification"
[CCS'24] Official Implementation of "Fisher Information guided Purification against Backdoor Attacks"
Unofficial implementation of the detector cleanse in the paper "BadDet: Backdoor Attacks on Object Detection."
Mask and Restore: Blind Backdoor Defense at Test Time with Masked Autoencoder
Official implementation of the NeurIPS 24 paper "Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor"
Implementation of ICCV'23 paper on Multimodal Backdoor Defense Technique: TIJO (Trigger Inversion using Joint Optimization)
Add a description, image, and links to the backdoor-defense topic page so that developers can more easily learn about it.
To associate your repository with the backdoor-defense topic, visit your repo's landing page and select "manage topics."