Random Projections for Improved Adversarial Robustness
Not on the map. Why?
Abstract (arXiv)
We propose two training techniques for improving the robustness of Neural Networks to adversarial attacks, i.e. manipulations of the inputs that are maliciously crafted to fool networks into incorrect predictions. Both methods are independent of the chosen attack and leverage random projections of the original inputs, with the purpose of exploiting both dimensionality reduction and some characteristic geometrical properties of adversarial perturbations. The first technique is called RP-Ensemble and consists of an ensemble of networks trained on multiple projected versions of the original inputs. The second one, named RP-Regularizer, adds instead a regularization term to the training objective.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 40 references that are in the map. First posted on arXiv 18 Feb 2021.
Builds on
21 of 40 references.
References · 21
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2013Intriguing properties of neural networkscited by 5,155
- 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
- 2016Simple and Scalable Predictive Uncertainty Estimation using Deep Ensemblescited by 3,926
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2016Adversarial examples in the physical worldcited by 1,769
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
- 2019On Evaluating Adversarial Robustnesscited by 447
- 2017Mitigating Adversarial Effects Through Randomizationcited by 383
- 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
- 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
- 2017Towards Robust Neural Networks via Random Self-ensemblecited by 159
9 more
- 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 125
- 2015Analysis of classifiers' robustness to adversarial perturbationscited by 76
- 2020Robustness of Bayesian Neural Networks to Gradient-Based Attackscited by 48
- 2018On the Geometry of Adversarial Examplescited by 43
- 2018Improved robustness to adversarial examples using Lipschitz regularization of the losscited by 13
- 2018Sufficient Conditions for Idealised Models to Have No Adversarial Examples: a Theoretical and Empirical Study with Bayesian Neural Networkscited by 9
- 2018Bayesian Adversarial Spheres: Bayesian Inference and Adversarial Examples in a Noiseless Settingcited by 8
- 2018High Dimensional Spaces, Deep Learning and Adversarial Examplescited by 5
- 2019Robust Neural Networks using Randomized Adversarial Trainingcited by 4
Built on by
Citing papers per year: 2023: 1.
1 paper.