GitHub·Code·MIT

kenny-co/sgd-uap-torch

Universal Adversarial Perturbations (UAPs) for PyTorch

50 stars·Updated Jul 2026
adversarial-attacksadversarial-examplesadversarial-machine-learningdeep-learning-securitydeep-neural-networksimage-classificationpytorchuniversal-adversarial-perturbationsuniversal-attacks
Open on GitHub

Linked papers

Code

Universal Adversarial Robustness of Texture and Shape-Biased Models

ICIP · 2021

Why Lacuna links this resource
Confirmed by the paper and resource

The paper explicitly provides the GitHub repository URL as its code release. The repository's README explicitly states that it contains the sample code, notebooks, and pre-computed UAPs for this paper, alongside another paper, making it a bundled resource.