Defenses Against Multi-Sticker Physical Domain Attacks on Classifiers
Not on the map. Why?
Abstract (arXiv)
Recently, physical domain adversarial attacks have drawn significant attention from the machine learning community. One important attack proposed by Eykholt et al. can fool a classifier by placing black and white stickers on an object such as a road sign. While this attack may pose a significant threat to visual classifiers, there are currently no defenses designed to protect against this attack. In this paper, we propose new defenses that can protect against multi-sticker attacks. We present defensive strategies capable of operating when the defender has full, partial, and no prior information about the attack. By conducting extensive experiments, we show that our proposed defenses can outperform existing defenses against physical attacks when presented with a multi-sticker attack.
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 31 of its 38 references that are in the map. First posted on arXiv 26 Jan 2021.
Builds on
31 of 38 references.
References · 31
- 2014Explaining and Harnessing Adversarial Examplescited by 7,287
- 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
- 2013Intriguing properties of neural networkscited by 5,114
- 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
- 2016Adversarial examples in the physical worldcited by 1,762
- 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
- 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 774
- 2016Universal adversarial perturbationscited by 774
- 2015Distillation as a Defense to Adversarial Perturbations against Deep Neural Networkscited by 675
- 2017One pixel attack for fooling deep neural networkscited by 579
19 more
- 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
- 2017Countering Adversarial Images using Input Transformationscited by 517
- 2017Adversarial Patchcited by 514
- 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 484
- 2018Certified Defenses against Adversarial Examplescited by 305
- 2017Detecting Adversarial Samples from Artifactscited by 244
- 2016A study of the effect of JPG compression on adversarial imagescited by 196
- 2018Stochastic Activation Pruning for Robust Adversarial Defensecited by 171
- 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
- 2018LaVAN: Localized and Visible Adversarial Noisecited by 112
- 2020Certified Defenses for Adversarial Patchescited by 100
- 2020(De)Randomized Smoothing for Certifiable Defense against Patch Attackscited by 97
- 2016Measuring Neural Net Robustness with Constraintscited by 90
- 2018Local Gradients Smoothing: Defense against localized adversarial attackscited by 85
- 2018Shield: Fast, Practical Defense and Vaccination for Deep Learning using JPEG Compressioncited by 74
- 2017Adversarial examples for generative modelscited by 58
- 2015Towards Vision-Based Deep Reinforcement Learning for Robotic Motion Controlcited by 33
- 2019LanCe: A Comprehensive and Lightweight CNN Defense Methodology against Physical Adversarial Attacks on Embedded Multimedia Applicationscited by 15
- 2018Defending against Adversarial Images using Basis Functions Transformationscited by 11
Built on by
Citing papers per year: 2021: 1; 2022: 1.
2 papers.