mlsanityData to 7 Oct 2026

Opportunities and Challenges in Deep Learning Adversarial Robustness: A Survey

arXiv 2007.00753 ↗First posted 1 Jul 2020cs.LG cs.AI stat.MLcited by 71

Not on the map. Why?

Abstract (arXiv)

As we seek to deploy machine learning models beyond virtual and controlled domains, it is critical to analyze not only the accuracy or the fact that it works most of the time, but if such a model is truly robust and reliable. This paper studies strategies to implement adversary robustly trained algorithms towards guaranteeing safety in machine learning algorithms. We provide a taxonomy to classify adversarial attacks and defenses, formulate the Robust Optimization problem in a min-max setting and divide it into 3 subcategories, namely: Adversarial (re)Training, Regularization Approach, and Certified Defenses. We survey the most recent and important results in adversarial example generation, defense mechanisms with adversarial (re)Training as their main defense against perturbations. We also survey mothods that add regularization terms that change the behavior of the gradient, making it harder for attackers to achieve their objective. Alternatively, we've surveyed methods which formally derive certificates of robustness by exactly solving the optimization problem or by approximations using upper or lower bounds. In addition, we discuss the challenges faced by most of the recent algorithms presenting future research perspectives.

Key facts. Cited by 71 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 14; 2023: 19; 2024: 17; 2025: 9; 2026: 4.

71 papers.

Sort:

By area:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  2. 2021Trustworthy AI: From Principles to Practicescited by 206
  3. 2024DynaMath: A Dynamic Visual Benchmark for Evaluating Mathematical Reasoning Robustness of Vision Language Modelscited by 143
  4. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  5. 2021Evaluating the Robustness of Semantic Segmentation for Autonomous Driving against Real-World Adversarial Patch Attackscited by 55
  6. 2023Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forwardcited by 28
  7. 2023Large Language Models of Code Fail at Completing Code with Potential Bugscited by 28
  8. 2021Techniques for Symbol Grounding with SATNetcited by 24
  9. 2023A Survey on the Robustness of Computer Vision Models against Common Corruptionscited by 20
  10. 2022Zero-Query Transfer Attacks on Context-Aware Object Detectorscited by 17
  11. 2024Robust Yet Efficient Conformal Prediction Setscited by 16
  12. 2023Resilient Constrained Learningcited by 15
38 more
  1. 2022Improving Robustness by Enhancing Weak Subnetscited by 12
  2. 2022Pruning Adversarially Robust Neural Networks without Adversarial Examplescited by 12
  3. 2023Domain Generalization in Machine Learning Models for Wireless Communications: Concepts, State-of-the-Art, and Open Issuescited by 12
  4. 2024Benchmarking the Robustness of Temporal Action Detection Models Against Temporal Corruptionscited by 12
  5. 2024Failures Are Fated, But Can Be Faded: Characterizing and Mitigating Unwanted Behaviors in Large-Scale Vision and Language Modelscited by 11
  6. 2021Model Preserving Compression for Neural Networkscited by 9
  7. 2023A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigmcited by 9
  8. 2022Defending Black-box Skeleton-based Human Activity Classifierscited by 8
  9. 2023Threatening Patch Attacks on Object Detection in Optical Remote Sensing Imagescited by 8
  10. 2023Understanding the robustness difference between stochastic gradient descent and adaptive gradient methodscited by 8
  11. 2023Untargeted White-box Adversarial Attack with Heuristic Defence Methods in Real-time Deep Learning based Network Intrusion Detection Systemcited by 8
  12. 2024Machine Learning Robustness: A Primercited by 8
  13. 2023Data Optimization in Deep Learning: A Surveycited by 6
  14. 2024Out-of-Distribution Data: An Acquaintance of Adversarial Examples -- A Surveycited by 6
  15. 2024Understanding Model Ensemble in Transferable Adversarial Attackcited by 6
  16. 2025Learning for routing: A guided review of recent developments and future directionscited by 6
  17. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  18. 2024Maintaining Adversarial Robustness in Continuous Learningcited by 5
  19. 2024Towards Certification of Uncertainty Calibration under Adversarial Attackscited by 5
  20. 2025Unveiling and Mitigating Adversarial Vulnerabilities in Iterative Optimizerscited by 4
  21. 2022Adversarial Robustness in Deep Learning: Attacks on Fragile Neuronscited by 3
  22. 2022Learning Neural Networks under Input-Output Specificationscited by 3
  23. 2022Inverse-Inverse Reinforcement Learning. How to Hide Strategy from an Adversarial Inverse Reinforcement Learnercited by 3
  24. 2022FuncFooler: A Practical Black-box Attack Against Learning-based Binary Code Similarity Detection Methodscited by 3
  25. 2023MLOps Spanning Whole Machine Learning Life Cycle: A Surveycited by 3
  26. 2023Improving Robustness Against Adversarial Attacks with Deeply Quantized Neural Networkscited by 3
  27. 2023HoSNN: Adversarially-Robust Homeostatic Spiking Neural Networks with Adaptive Firing Thresholdscited by 3
  28. 2023Rethinking Robustness of Model Attributionscited by 3
  29. 2024A Black Swan Hypothesis: The Role of Human Irrationality in AI Safetycited by 3
  30. 2023Towards Certified Probabilistic Robustness with High Accuracycited by 2
  31. 2023Fairness under Covariate Shift: Improving Fairness-Accuracy tradeoff with few Unlabeled Test Samplescited by 2
  32. 2024Causal Feature Selection for Responsible Machine Learningcited by 2
  33. 2025Stop Walking in Circles! Bailing Out Early in Projected Gradient Descentcited by 2
  34. 2021Adaptive Clustering of Robust Semantic Representations for Adversarial Image Purificationcited by 1
  35. 2022Semi-Implicit Hybrid Gradient Methods with Application to Adversarial Robustnesscited by 1
  36. 2022Isometric Representations in Neural Networks Improve Robustnesscited by 1
  37. 2022MAViC: Multimodal Active Learning for Video Captioningcited by 1
  38. 2023ScAR: Scaling Adversarial Robustness for LiDAR Object Detectioncited by 1

50 most cited of 71 All 71 (JSON)