um-dsp / MorphenceLinks
Morphence: An implementation of a moving target defense against adversarial example attacks demonstrated for image classification models trained on MNIST and CIFAR-10.
☆23Updated 9 months ago
Alternatives and similar repositories for Morphence
Users that are interested in Morphence are comparing it to the libraries listed below
Sorting:
- Example of the attack described in the paper "Towards Poisoning of Deep Learning Algorithms with Back-gradient Optimization"☆21Updated 5 years ago
- Foolbox implementation for NeurIPS 2021 Paper: "Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraints".☆25Updated 3 years ago
- Code for "On the Trade-off between Adversarial and Backdoor Robustness" (NIPS 2020)☆17Updated 4 years ago
- The code is for our NeurIPS 2019 paper: https://arxiv.org/abs/1910.04749☆34Updated 5 years ago
- Prediction Poisoning: Towards Defenses Against DNN Model Stealing Attacks (ICLR '20)☆31Updated 4 years ago