[ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
-
Updated
Jun 5, 2024 - Python
[ICML 2024] Unsupervised Adversarial Fine-Tuning of Vision Embeddings for Robust Large Vision-Language Models
👀🛡️ Code for the paper “Carefully Blending Adversarial Training and Purification Improves Adversarial Robustness” by Emanuele Ballarin, Alessio Ansuini and Luca Bortolussi (2024)
Machine Learning Attack Series
Code for the paper "Multi-scale Diffusion Denoised Smoothing" (NeurIPS 2023)
auto_LiRPA: An Automatic Linear Relaxation based Perturbation Analysis Library for Neural Networks and General Computational Graphs
Must-read Papers on Textual Adversarial Attack and Defense
Simple code related to adversarial examples, attacks, and defenses.
[CIKM 2023] GUARD: Graph Universal Adversarial Defense
Adversarial defense by retreaval-based methods
Adversarial Attack and Defense in Deep Ranking, T-PAMI, 2024
Implementation of the paper "Improving the Accuracy-Robustness Trade-off of Classifiers via Adaptive Smoothing".
[Pattern Recognition 2024] Towards Robust Neural Networks via Orthogonal Diversity"
A modified model for self-driving car that is resilient to adversarial attacks
Feature Separation and Recalibration (CVPR 2023 Highlights)
An efficient framework for establishing baselines in standard and adversarial machine learning training projects
[ICLR 2021] "InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective" by Boxin Wang, Shuohang Wang, Yu Cheng, Zhe Gan, Ruoxi Jia, Bo Li, Jingjing Liu
Code for the paper: Adversarial Training Against Location-Optimized Adversarial Patches. ECCV-W 2020.
Official PyTorch implementation of "Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attacks" (AAAI 2022)
GARNET: Reduced-Rank Topology Learning for Robust and Scalable Graph Neural Networks
Tensors-based framework for adversarial robustness
Add a description, image, and links to the adversarial-defense topic page so that developers can more easily learn about it.
To associate your repository with the adversarial-defense topic, visit your repo's landing page and select "manage topics."