Boosting Adversarial Robustness using Feature Level Stochastic Smoothing
Not on the map. Why?
Abstract (arXiv)
Advances in adversarial defenses have led to a significant improvement in the robustness of Deep Neural Networks. However, the robust accuracy of present state-ofthe-art defenses is far from the requirements in critical applications such as robotics and autonomous navigation systems. Further, in practical use cases, network prediction alone might not suffice, and assignment of a confidence value for the prediction can prove crucial. In this work, we propose a generic method for introducing stochasticity in the network predictions, and utilize this for smoothing decision boundaries and rejecting low confidence predictions, thereby boosting the robustness on accepted samples. The proposed Feature Level Stochastic Smoothing based classification also results in a boost in robustness without rejection over existing adversarial training methods. Finally, we combine the proposed method with adversarial detection methods, to achieve the benefits of both approaches.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 31 of its 40 references that are in the map. First posted on arXiv 10 Jun 2023.
Builds on
31 of 40 references.
References · 31
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
- 2013Auto-Encoding Variational Bayescited by 4,053
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
- 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
- 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
- 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
- 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
- 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
19 more
- 2020Overfitting in adversarially robust deep learningcited by 506
- 2017Regularizing Neural Networks by Penalizing Confident Output Distributionscited by 464
- 2019On Evaluating Adversarial Robustnesscited by 447
- 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
- 2017Mitigating Adversarial Effects Through Randomizationcited by 383
- 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 334
- 2018Adversarially Robust Generalization Requires More Datacited by 318
- 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
- 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
- 2020Bag of Tricks for Adversarial Trainingcited by 200
- 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
- 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 125
- 2019The Odds are Odd: A Statistical Test for Detecting Adversarial Examplescited by 75
- 2020Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defensescited by 62
- 2015Adversarial Manipulation of Deep Representationscited by 56
- 2019A New Defense Against Adversarial Images: Turning a Weakness into a Strengthcited by 49
- 2020Random Smoothing Might be Unable to Certify ℓ_∞ Robustness for High-Dimensional Imagescited by 35
- 2018Resisting Adversarial Attacks using Gaussian Mixture Variational Autoencoderscited by 26
- 2016Rank Verification for Exponential Familiescited by 13
Built on by
Not cited yet.