Generalized Data-free Universal Adversarial Perturbations

Task-agnostic universal black-box attacks on computer vision neural network via procedural noise (CCS'19)

Universal Adversarial Perturbations (UAPs) for PyTorch

Official implementation of the ICCV2023 paper: Enhancing Generalization of Universal Adversarial Perturbation through Gradient Aggregation

PyTorch Implementation of Stereoscopic Universal Perturbations across Different Architectures and Datasets (CVPR 2022)

Generalized Data-free Universal Adversarial Perturbations in PyTorch

Universal Adversarial Audio Perturbations

Code implementing the experiments described in the NeurIPS 2018 paper "With Friends Like These, Who Needs Adversaries?".

Official implementation of "Resilience of Autonomous Vehicle Object Category Detections to Universal Adversarial Perturbations"

Universal adversarial attack on NLP model

Evaluation of various defence mechanisms and various UAPs. Done as a part of GD-UAP.