mlsanityData to 7 Oct 2026

Fast Training of Provably Robust Neural Networks by SingleProp

arXiv 2102.01208 ↗First posted 1 Feb 2021cs.LG stat.MLcited by 5

Not on the map. Why?

Abstract (arXiv)

Recent works have developed several methods of defending neural networks against adversarial attacks with certified guarantees. However, these techniques can be computationally costly due to the use of certification during training. We develop a new regularizer that is both more efficient than existing certified defenses, requiring only one additional forward propagation through a network, and can be used to train networks with similar certified accuracy. Through experiments on MNIST and CIFAR-10 we demonstrate improvements in training speed and comparable certified accuracy compared to state-of-the-art certified defenses.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 29 of its 40 references that are in the map. First posted on arXiv 1 Feb 2021.

Builds on

29 of 40 references.

References · 29

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  9. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  10. 2017One pixel attack for fooling deep neural networkscited by 579
  11. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  12. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
17 more
  1. 2017Certifying Some Distributional Robustness with Principled Adversarial Trainingcited by 333
  2. 2018Certified Defenses against Adversarial Examplescited by 305
  3. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  4. 2019Towards Stable and Efficient Training of Verifiably Robust Neural Networkscited by 204
  5. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  6. 2018Efficient Formal Safety Analysis of Neural Networkscited by 165
  7. 2017EAD: Elastic-Net Attacks to Deep Neural Networks via Adversarial Examplescited by 154
  8. 2018Scaling provable adversarial defensescited by 141
  9. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  10. 2019A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networkscited by 124
  11. 2017Maximum Resilience of Artificial Neural Networkscited by 97
  12. 2018Training for Faster Adversarial Robustness Verification via Inducing ReLU Stabilitycited by 67
  13. 2018Structured Adversarial Attack: Towards General Implementation and Better Interpretabilitycited by 63
  14. 2018Training verified learners with learned verifierscited by 50
  15. 2018CNN-Cert: An Efficient Framework for Certifying Robustness of Convolutional Neural Networkscited by 50
  16. 2019POPQORN: Quantifying Robustness of Recurrent Neural Networkscited by 36
  17. 2017Evaluating Robustness of Neural Networks with Mixed Integer Programmingcited by 14

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 1; 2023: 1; 2024: 1.

5 papers.

  1. 2021Learning Security Classifiers with Verified Global Robustness Propertiescited by 14
  2. 2022Holistic Adversarial Robustness of Deep Learning Modelscited by 11
  3. 2021The Fundamental Limits of Interval Arithmetic for Neural Networkscited by 4
  4. 2024On Using Certified Training towards Empirical Robustnesscited by 3
  5. 2023Can Adversarial Examples Be Parsed to Reveal Victim Model Information?cited by 1