Advocating for Multiple Defense Strategies against Adversarial Examples
Not on the map. Why?
Abstract (arXiv)
It has been empirically observed that defense mechanisms designed to protect neural networks against ℓ_∞ adversarial examples offer poor performance against ℓ2 adversarial examples and vice versa. In this paper we conduct a geometrical analysis that validates this observation. Then, we provide a number of empirical insights to illustrate the effect of this phenomenon in practice. Then, we review some of the existing defense mechanism that attempts to defend against multiple attacks by mixing defense strategies. Thanks to our numerical experiments, we discuss the relevance of this method and state open questions for the adversarial examples community.
Key facts. Cited by 11 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Dec 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 2; 2022: 2; 2023: 5; 2024: 0; 2025: 1; 2026: 1.
11 papers.
- 2023R-LPIPS: An Adversarially Robust Perceptual Similarity Metriccited by 27
- 2023LipSim: A Provably Robust Perceptual Similarity Metriccited by 15
- 2021Adversarial Robustness by Design through Analog Computing and Synthetic Gradientscited by 7
- 2023PubDef: Defending Against Transfer Attacks From Public Modelscited by 7
- 2022Game Theoretic Mixed Experts for Combinational Adversarial Machine Learningcited by 6
- 2023Certification of Deep Learning Models for Medical Image Segmentationcited by 4
- 2021ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradientscited by 2
- 2022Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysiscited by 2
- 2023Towards Better Certified Segmentation via Diffusion Modelscited by 2
- 2025On the Trade-Off Between Transparency and Security in Adversarial Machine Learningcited by 0
- 2026Frame the adversary: a structure-aware attack methodologycited by 0
- 2026Frame the adversary: a structure-aware attack methodology25 Sep 2026
- 2025On the Trade-Off Between Transparency and Security in Adversarial Machine Learning14 Nov 2025
- 2023LipSim: A Provably Robust Perceptual Similarity Metric27 Oct 2023
- 2023PubDef: Defending Against Transfer Attacks From Public Models26 Oct 2023
- 2023Certification of Deep Learning Models for Medical Image Segmentation5 Oct 2023
- 2023R-LPIPS: An Adversarially Robust Perceptual Similarity Metric27 Jul 2023
- 2023Towards Better Certified Segmentation via Diffusion Models16 Jun 2023
- 2022Game Theoretic Mixed Experts for Combinational Adversarial Machine Learning26 Nov 2022
- 2022Towards Evading the Limits of Randomized Smoothing: A Theoretical Analysis3 Jun 2022
- 2021ROPUST: Improving Robustness through Fine-tuning with Photonic Processors and Synthetic Gradients6 Jul 2021
- 2021Adversarial Robustness by Design through Analog Computing and Synthetic Gradients6 Jan 2021