mlsanityData to 7 Oct 2026

An Overview and Prospective Outlook on Robust Training and Certification of Machine Learning Models

arXiv 2208.07464 ↗First posted 15 Aug 2022cs.LG math.OC stat.MLcited by 1

Not on the map. Why?

Abstract (arXiv)

In this discussion paper, we survey recent research surrounding robustness of machine learning models. As learning algorithms become increasingly more popular in data-driven control systems, their robustness to data uncertainty must be ensured in order to maintain reliable safety-critical operations. We begin by reviewing common formalisms for such robustness, and then move on to discuss popular and state-of-the-art techniques for training robust machine learning models as well as methods for provably certifying such robustness. From this unification of robust machine learning, we identify and discuss pressing directions for future research in the area.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 82 of its 122 references that are in the map. First posted on arXiv 15 Aug 2022.

Builds on

82 of 122 references.

References · 82

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  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. 2021Convex optimizationcited by 2,479
  7. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  10. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  11. 2017A Closer Look at Memorization in Deep Networkscited by 936
  12. 2016Adversarial Machine Learning at Scalecited by 934
38 more
  1. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  2. 2018Robustness May Be at Odds with Accuracycited by 873
  3. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  4. 2017Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networkscited by 739
  5. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  6. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  7. 2017One pixel attack for fooling deep neural networkscited by 579
  8. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  9. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  10. 2017Adversarial Patchcited by 514
  11. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  12. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  13. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  14. 2018Efficient Neural Network Robustness Certification with General Activation Functionscited by 439
  15. 2019Provably Robust Deep Learning via Adversarially Trained Smoothed Classifierscited by 328
  16. 2018On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Modelscited by 322
  17. 2020Performative Predictioncited by 318
  18. 2017Adversarial Attacks on Neural Network Policiescited by 314
  19. 2019Efficient and Accurate Estimation of Lipschitz Constants for Deep Neural Networkscited by 290
  20. 2014Caffe: Convolutional Architecture for Fast Feature Embeddingcited by 287
  21. 2015Data-driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulationscited by 285
  22. 2018Towards Fast Computation of Certified Robustness for ReLU Networkscited by 254
  23. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 224
  24. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  25. 2016Statistics of Robust Optimization: A Generalized Empirical Likelihood Approachcited by 182
  26. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  27. 2018Certified Adversarial Robustness with Additive Noisecited by 178
  28. 2018Semidefinite relaxations for certifying robustness to adversarial examplescited by 178
  29. 2018Efficient Formal Safety Analysis of Neural Networkscited by 165
  30. 2020Randomized Smoothing of All Shapes and Sizescited by 146
  31. 2018Scaling provable adversarial defensescited by 141
  32. 2018A Dual Approach to Scalable Verification of Deep Networkscited by 125
  33. 2015Distributionally Robust Logistic Regressioncited by 124
  34. 2019A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networkscited by 124
  35. 2014Return of the Devil in the Details: Delving Deep into Convolutional Netscited by 122
  36. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  37. 2019Safety Verification and Robustness Analysis of Neural Networks via Quadratic Constraints and Semidefinite Programmingcited by 100
  38. 2020Neural Networks are Convex Regularizers: Exact Polynomial-time Convex Optimization Formulations for Two-layer Networkscited by 96

50 most cited of 82 All 82 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 1.

1 paper.

  1. 2025Risk Analysis and Design Against Adversarial Actionscited by 2