The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)
-
Updated
Jul 18, 2024 - Python
The code for ACM MM2024 (Multimodal Unlearnable Examples: Protecting Data against Multimodal Contrastive Learning)
FedDefender is a novel defense mechanism designed to safeguard Federated Learning from the poisoning attacks (i.e., backdoor attacks).
A Survey of Poisoning Attacks and Defenses in Recommender Systems
Official Website of https://github.com/tamlhp/awesome-recsys-poisoning
Paper "An LLM-Assisted Easy-to-Trigger Poisoning Attack on Code Completion Models: Injecting Disguised Vulnerabilities against Strong Detection"
[UbiComp/IMWUT '23] Hierarchical Clustering-based Personalized Federated Learning for Robust and Fair Human Activity Recognition
Explanation-Guided Backdoor Poisoning Attacks Against Malware Classifiers: Verification and Testing (university project for Cybersecurity)
Source code for our paper "Leveraging Diffusion-Based Image Variations for Robust Training on Poisoned Data" (NeurIPS 2023 Workshop).
My experiments in weaponizing ONOS applications (https://github.com/opennetworkinglab/onos)
This repository contains the code for our USENIX Security'23 paper "PORE: Provably Robust Recommender Systems against Data Poisoning Attacks"
Venom is an ARP-Poisoner that sniffs TLS requests to take advantage of SNI Leak and display all targets DNS traffic even if it is encrypted.
A repository to quickly generate synthetic data and associated trojaned deep learning models
Adversarial-Attacks-and-Defence
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.
Membership inference attacks on (poisoned) segmentation models; master's thesis
Research work on biometric security and template updation using Machine Learning.
Can Adversarial training defend against Poisoning attacks?
Simulation of FL in python for Digit Recognition ML model. Simulated poisoning attacks and studies their impact.
Add a description, image, and links to the poisoning-attack topic page so that developers can more easily learn about it.
To associate your repository with the poisoning-attack topic, visit your repo's landing page and select "manage topics."