Attacking the Madry Defense Model with L1-based Adversarial Examples
Not on the map. Why?
Abstract (arXiv)
The Madry Lab recently hosted a competition designed to test the robustness of their adversarially trained MNIST model. Attacks were constrained to perturb each pixel of the input image by a scaled maximal L_∞ distortion ε = 0.3. This discourages the use of attacks which are not optimized on the L_∞ distortion metric. Our experimental results demonstrate that by relaxing the L_∞ constraint of the competition, the elastic-net attack to deep neural networks (EAD) can generate transferable adversarial examples which, despite their high average L_∞ distortion, have minimal visual distortion. These results call into question the use of L_∞ as a sole measure for visual distortion, and further demonstrate the power of EAD at generating robust adversarial examples.
Key facts. Cited by 21 papers in the map (data through 14 Oct 2026). First posted on arXiv 30 Oct 2017.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 6; 2022: 8; 2023: 5; 2024: 1; 2025: 1.
21 papers.
Sort:
By area:
- 2021Machine learning pipeline for battery state of health estimationcited by 29
- 2022Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbationscited by 26
- 2021Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attackscited by 20
- 2022Pixle: a fast and effective black-box attack based on rearranging pixelscited by 20
- 2022On the benefits of knowledge distillation for adversarial robustnesscited by 18
- 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directionscited by 11
- 2022Analysis and Extensions of Adversarial Training for Video Classificationcited by 11
- 2021A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustnesscited by 6
- 2023Adversarial Learning in Real-World Fraud Detection: Challenges and Perspectivescited by 5
- 2023Training on Foveated Images Improves Robustness to Adversarial Attackscited by 5
- 2022Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perceptioncited by 3
- 2024A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defensecited by 3
9 more
- 2023Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddingscited by 2
- 2025FrameShield: Adversarially Robust Video Anomaly Detectioncited by 2
- 2021Using Undervolting as an On-Device Defense Against Adversarial Machine Learning Attackscited by 1
- 2023Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Modelcited by 1
- 2021HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attackscited by 0
- 2021Group-Structured Adversarial Trainingcited by 0
- 2022Art-Attack: Black-Box Adversarial Attack via Evolutionary Artcited by 0
- 2022DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learningcited by 0
- 2023Fixed Inter-Neuron Covariability Induces Adversarial Robustnesscited by 0
- 2025FrameShield: Adversarially Robust Video Anomaly Detection24 Oct 2025
- 2024A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense11 Feb 2024
- 2023Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model28 Nov 2023
- 2023Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddings4 Sep 2023
- 2023Fixed Inter-Neuron Covariability Induces Adversarial Robustness7 Aug 2023
- 2023Training on Foveated Images Improves Robustness to Adversarial Attacks1 Aug 2023
- 2023Adversarial Learning in Real-World Fraud Detection: Challenges and Perspectives3 Jul 2023
- 2022DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning31 Jul 2022
- 2022Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perception26 Jul 2022
- 2022Analysis and Extensions of Adversarial Training for Video Classification16 Jun 2022
- 2022On the benefits of knowledge distillation for adversarial robustness14 Mar 2022
- 2022Art-Attack: Black-Box Adversarial Attack via Evolutionary Art7 Mar 2022
9 more
- 2022Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations9 Feb 2022
- 2022Pixle: a fast and effective black-box attack based on rearranging pixels4 Feb 2022
- 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directions3 Jan 2022
- 2021Using Undervolting as an On-Device Defense Against Adversarial Machine Learning Attacks20 Jul 2021
- 2021Group-Structured Adversarial Training18 Jun 2021
- 2021HASI: Hardware-Accelerated Stochastic Inference, A Defense Against Adversarial Machine Learning Attacks9 Jun 2021
- 2021Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attacks18 May 2021
- 2021A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustness1 Mar 2021
- 2021Machine learning pipeline for battery state of health estimation1 Feb 2021
- 2021Machine learning pipeline for battery state of health estimationcited by 29
- 2022Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbationscited by 26
- 2021Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attackscited by 20
- 2022Pixle: a fast and effective black-box attack based on rearranging pixelscited by 20
- 2022Robust Natural Language Processing: Recent Advances, Challenges, and Future Directionscited by 11
- 2022Analysis and Extensions of Adversarial Training for Video Classificationcited by 11
- 2021A Multiclass Boosting Framework for Achieving Fast and Provable Adversarial Robustnesscited by 6
- 2023Adversarial Learning in Real-World Fraud Detection: Challenges and Perspectivescited by 5
- 2023Training on Foveated Images Improves Robustness to Adversarial Attackscited by 5
- 2022Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perceptioncited by 3
- 2024A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defensecited by 3
- 2023Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddingscited by 2
12 most cited of 20 All 20 (JSON)
- 2025FrameShield: Adversarially Robust Video Anomaly Detection24 Oct 2025
- 2024A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defense11 Feb 2024
- 2023Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Model28 Nov 2023
- 2023Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddings4 Sep 2023
- 2023Fixed Inter-Neuron Covariability Induces Adversarial Robustness7 Aug 2023
- 2023Training on Foveated Images Improves Robustness to Adversarial Attacks1 Aug 2023
- 2023Adversarial Learning in Real-World Fraud Detection: Challenges and Perspectives3 Jul 2023
- 2022DNNShield: Dynamic Randomized Model Sparsification, A Defense Against Adversarial Machine Learning31 Jul 2022
- 2022Perception-Aware Attack: Creating Adversarial Music via Reverse-Engineering Human Perception26 Jul 2022
- 2022Analysis and Extensions of Adversarial Training for Video Classification16 Jun 2022
- 2022Art-Attack: Black-Box Adversarial Attack via Evolutionary Art7 Mar 2022
- 2022Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations9 Feb 2022
12 newest of 20 All 20 (JSON)