mlsanityData to 7 Oct 2026

Breaking certified defenses: Semantic adversarial examples with spoofed robustness certificates

arXiv 2003.08937 ↗First posted 19 Mar 2020cs.LG stat.MLcited by 17

Not on the map. Why?

Abstract (arXiv)

To deflect adversarial attacks, a range of "certified" classifiers have been proposed. In addition to labeling an image, certified classifiers produce (when possible) a certificate guaranteeing that the input image is not an ℓp-bounded adversarial example. We present a new attack that exploits not only the labelling function of a classifier, but also the certificate generator. The proposed method applies large perturbations that place images far from a class boundary while maintaining the imperceptibility property of adversarial examples. The proposed "Shadow Attack" causes certifiably robust networks to mislabel an image and simultaneously produce a "spoofed" certificate of robustness.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 4; 2022: 3; 2023: 5; 2024: 5.

17 papers.

Sort:

By area:

  1. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 608
  2. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  3. 2021ML Attack Models: Adversarial Attacks and Data Poisoning Attackscited by 23
  4. 2022Unrestricted Black-box Adversarial Attack Using GAN with Limited Queriescited by 18
  5. 2022Why adversarial training can hurt robust accuracycited by 12
  6. 2021Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attackscited by 4
  7. 2024Transcending Adversarial Perturbations: Manifold-Aided Adversarial Examples with Legitimate Semanticscited by 4
  8. 2023Benchmarking Adversarial Robustness of Compressed Deep Learning Modelscited by 3
  9. 2024COMMIT: Certifying Robustness of Multi-Sensor Fusion Systems against Semantic Attackscited by 2
  10. 2024Rethinking the Threat and Accessibility of Adversarial Attacks against Face Recognition Systemscited by 2
  11. 2022Tightening Robustness Verification of MaxPool-based Neural Networks via Minimizing the Over-Approximation Zonecited by 1
  12. 2023A reading survey on adversarial machine learning: Adversarial attacks and their understandingcited by 1
5 more
  1. 2024How to beat a Bayesian adversarycited by 1
  2. 2021Group-Structured Adversarial Trainingcited by 0
  3. 2023Adversarial attacks on hybrid classical-quantum Deep Learning models for Histopathological Cancer Detectioncited by 0
  4. 2023General Lipschitz: Certified Robustness Against Resolvable Semantic Transformations via Transformation-Dependent Randomized Smoothingcited by 0
  5. 2024Towards General Robustness Verification of MaxPool-based Convolutional Neural Networks via Tightening Linear Approximationcited by 0