mlsanityData to 14 Oct 2026

Et Tu Certifications: Robustness Certificates Yield Better Adversarial Examples

arXiv 2302.04379 ↗First posted 9 Feb 2023cs.LG cs.CRcited by 4

Not on the map. Why?

Abstract (arXiv)

In guaranteeing the absence of adversarial examples in an instance's neighbourhood, certification mechanisms play an important role in demonstrating neural net robustness. In this paper, we ask if these certifications can compromise the very models they help to protect? Our new Certification Aware Attack exploits certifications to produce computationally efficient norm-minimising adversarial examples 74 % more often than comparable attacks, while reducing the median perturbation norm by more than 10%. While these attacks can be used to assess the tightness of certification bounds, they also highlight that releasing certifications can paradoxically reduce security.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 23 of its 40 references that are in the map. First posted on arXiv 9 Feb 2023.

Builds on

23 of 40 references.

References · 23

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2013Intriguing properties of neural networkscited by 5,155
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  8. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  9. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  10. 2017Evasion Attacks against Machine Learning at Test Timecited by 689
  11. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  12. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 330
11 more
  1. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 255
  2. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 228
  3. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 195
  4. 2018Certified Adversarial Robustness with Additive Noisecited by 180
  5. 2019A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networkscited by 125
  6. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  7. 2020Certified Defenses for Adversarial Patchescited by 101
  8. 2020(De)Randomized Smoothing for Certifiable Defense against Patch Attackscited by 98
  9. 2018Motivating the Rules of the Game for Adversarial Example Researchcited by 57
  10. 2021Towards Evaluating and Training Verifiably Robust Neural Networkscited by 15
  11. 2022Double Bubble, Toil and Trouble: Enhancing Certified Robustness through Transitivitycited by 15

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 3; 2026: 1.

4 papers.

  1. 2025Fox in the Henhouse: Supply-Chain Backdoor Attacks Against Reinforcement Learningcited by 5
  2. 2025Position: Certified Robustness Does Not (Yet) Imply Model Securitycited by 4
  3. 2025Multi-level Certified Defense Against Poisoning Attacks in Offline Reinforcement Learningcited by 3
  4. 2026What Was That Again? Certified Robustness for Automatic Speech Recognitioncited by 0