对抗样本（Adversarial Examples）和投毒攻击（Poisoning Attacks）相关资料

Official implementation of "FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective".

A repository to quickly generate synthetic data and associated trojaned deep learning models

Official implementation of "FL-WBC: Enhancing Robustness against Model Poisoning Attacks in Federated Learning from a Client Perspective".

A Survey of Poisoning Attacks and Defenses in Recommender Systems

[UbiComp/IMWUT '23] Hierarchical Clustering-based Personalized Federated Learning for Robust and Fair Human Activity Recognition

Example of using ELF hacking to inject malicious code into a target binary

My experiments in weaponizing ONOS applications (https://github.com/opennetworkinglab/onos)

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

Source code for the Energy-Latency Attacks via Sponge Poisoning paper.

[ICLR2025] Detecting Backdoor Samples in Contrastive Language Image Pretraining

The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)

Code for "Biometric Backdoors: A Poisoning Attack Against Unsupervised Template Updating"

A Semi-supervised learning model (Ladder Network) to classify MNIST digits. A few attacks were executed on it with the target of misclassifying 4s with 9s.

Implementation of the dns cache poisoning attack reloaded (ACM CCS '20) replication.

An isolated environment for DNS cache poisoning attack investigation and demonstration.

[Preprint] On the Effectiveness of Mitigating Data Poisoning Attacks with Gradient Shaping

Official PyTorch implementation of "MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks"

USENIX Security'24 Paper Repo

[ACSAC '24] FedCAP: Robust Federated Learning via Customized Aggregation and Personalization