Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
-
Updated
May 16, 2024 - Python
Code relative to "Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks"
A list of papers in NeurIPS 2022 related to adversarial attack and defense / AI security.
Adaptive evaluation reveals that most examined adversarial defenses for GNNs show no or only marginal improvement in robustness. (NeurIPS, 2022)
PyTorch implementation of adversarial training and defenses [Fantastic Robustness Measures: The Secrets of Robust Generalization, NeurIPS 2023].
Official implementation of Segmentation and Complete (SAC) defense.
Official code for "PubDef: Defending Against Transfer Attacks From Public Models" (ICLR 2024)
A Python package for detecting adversarial evasion attacks
DeepDefend is an open-source Python library for adversarial attacks and defenses in deep learning models, enhancing the security and robustness of AI systems.
Simple code related to adversarial examples, attacks, and defenses.
Add a description, image, and links to the adversarial-defenses topic page so that developers can more easily learn about it.
To associate your repository with the adversarial-defenses topic, visit your repo's landing page and select "manage topics."