DA3G: Detecting Adversarial Attacks by Analysing Gradients
- 30 September 2021
- book chapter
- Published by Springer Nature
- p. 563-583
Abstract
No abstract availableKeywords
This publication has 18 references indexed in Scilit:
- ML-LOO: Detecting Adversarial Examples with Feature AttributionProceedings of the AAAI Conference on Artificial Intelligence, 2020
- One Pixel Attack for Fooling Deep Neural NetworksIEEE Transactions on Evolutionary Computation, 2019
- Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networks2018
- Adversarial Examples Are Not Easily Detected2017
- Towards Evaluating the Robustness of Neural Networks2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Deep Residual Learning for Image Recognition2016
- Deep neural networks are easily fooled: High confidence predictions for unrecognizable images2015
- Evasion Attacks against Machine Learning at Test Time2013
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998