mlsanityData to 14 Oct 2026

Exploring Misclassifications of Robust Neural Networks to Enhance Adversarial Attacks

arXiv 2105.10304 ↗First posted 21 May 2021cs.LGcited by 33

Not on the map. Why?

Abstract (arXiv)

Progress in making neural networks more robust against adversarial attacks is mostly marginal, despite the great efforts of the research community. Moreover, the robustness evaluation is often imprecise, making it difficult to identify promising approaches. We analyze the classification decisions of 19 different state-of-the-art neural networks trained to be robust against adversarial attacks. Our findings suggest that current untargeted adversarial attacks induce misclassification towards only a limited amount of different classes. Additionally, we observe that both over- and under-confidence in model predictions result in an inaccurate assessment of model robustness. Based on these observations, we propose a novel loss function for adversarial attacks that consistently improves attack success rate compared to prior loss functions for 19 out of 19 analyzed models.

Key facts. Cited by 33 papers in the map (data through 14 Oct 2026). Builds on 37 of its 57 references that are in the map. First posted on arXiv 21 May 2021.

Builds on

37 of 57 references.

References · 37

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  4. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  6. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  7. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  8. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  9. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
  10. 2020On Adaptive Attacks to Adversarial Example Defensescited by 555
  11. 2020Overfitting in adversarially robust deep learningcited by 506
  12. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
25 more
  1. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  2. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  3. 2020Uncovering the Limits of Adversarial Training against Norm-Bounded Adversarial Examplescited by 278
  4. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 243
  5. 2018Adversarial Risk and the Dangers of Evaluating Against Weak Attackscited by 221
  6. 2020Geometry-aware Instance-reweighted Adversarial Trainingcited by 198
  7. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 183
  8. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 172
  9. 2015Adding Gradient Noise Improves Learning for Very Deep Networkscited by 145
  10. 2020Self-Adaptive Training: beyond Empirical Risk Minimizationcited by 126
  11. 2019Imperceptible, Robust, and Targeted Adversarial Examples for Automatic Speech Recognitioncited by 124
  12. 2020Boosting Adversarial Training with Hypersphere Embeddingcited by 97
  13. 2020Learnable Boundary Guided Adversarial Trainingcited by 93
  14. 2019Adversarial Defense by Restricting the Hidden Space of Deep Neural Networkscited by 56
  15. 2021Fast Minimum-norm Adversarial Attacks through Adaptive Norm Constraintscited by 50
  16. 2019Accurate, reliable and fast robustness evaluationcited by 43
  17. 2018Greedy Attack and Gumbel Attack: Generating Adversarial Examples for Discrete Datacited by 38
  18. 2020Efficient Robust Training via Backward Smoothingcited by 29
  19. 2020Composite Adversarial Attackscited by 29
  20. 2021CLIP: Cheap Lipschitz Training of Neural Networkscited by 29
  21. 2021Identifying Untrustworthy Predictions in Neural Networks by Geometric Gradient Analysiscited by 13
  22. 2020Improved Gradient based Adversarial Attacks for Quantized Networkscited by 10
  23. 2020A Bayes-Optimal View on Adversarial Examplescited by 8
  24. 2020Manifold Regularization for Locally Stable Deep Neural Networkscited by 8
  25. 2020Dynamically Sampled Nonlocal Gradients for Stronger Adversarial Attackscited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 2; 2022: 6; 2023: 8; 2024: 6; 2025: 10; 2026: 1.

33 papers.

Sort:

By area:

  1. 2021Measure and Improve Robustness in NLP Models: A Surveycited by 107
  2. 2024Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Spacecited by 91
  3. 2023Adversarial Attacks and Defenses in Large Language Models: Old and New Threatscited by 49
  4. 2022DISCO: Adversarial Defense with Local Implicit Functionscited by 34
  5. 2022Universal Adversarial Examples in Remote Sensing: Methodology and Benchmarkcited by 24
  6. 2022Improving Robustness against Real-World and Worst-Case Distribution Shifts through Decision Region Quantificationcited by 16
  7. 2024DD-RobustBench: An Adversarial Robustness Benchmark for Dataset Distillationcited by 8
  8. 2025State-Aware Perturbation Optimization for Robust Deep Reinforcement Learningcited by 8
  9. 2022Behind the Machine's Gaze: Neural Networks with Biologically-inspired Constraints Exhibit Human-like Visual Attentioncited by 7
  10. 2023Raising the Bar for Certified Adversarial Robustness with Diffusion Modelscited by 7
  11. 2025Robust Deep Reinforcement Learning in Robotics via Adaptive Gradient-Masked Adversarial Attackscited by 7
  12. 2023AROID: Improving Adversarial Robustness Through Online Instance-Wise Data Augmentationcited by 6
21 more
  1. 2025Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attackscited by 6
  2. 2023Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Modelscited by 5
  3. 2025Benchmarking Unified Face Attack Detection via Hierarchical Prompt Tuningcited by 5
  4. 2025Byte Pair Encoding for Efficient Time Series Forecastingcited by 5
  5. 2023AFLOW: Developing Adversarial Examples under Extremely Noise-limited Settingscited by 4
  6. 2021Evaluating Adversarial Attacks on ImageNet: A Reality Check on Misclassification Classescited by 3
  7. 2024Unveiling AI's Blind Spots: An Oracle for In-Domain, Out-of-Domain, and Adversarial Errorscited by 3
  8. 2022Adversarial Contrastive Learning by Permuting Cluster Assignmentscited by 2
  9. 2023Towards Certified Probabilistic Robustness with High Accuracycited by 2
  10. 2024FoolSDEdit: Deceptively Steering Your Edits Towards Targeted Attribute-aware Distributioncited by 2
  11. 2025Effective Data Pruning through Score Extrapolationcited by 2
  12. 2023Spatial-Frequency Discriminability for Revealing Adversarial Perturbationscited by 1
  13. 2023IRAD: Implicit Representation-driven Image Resampling against Adversarial Attackscited by 1
  14. 2025How to Backdoor Image Knowledge Distillationcited by 1
  15. 2026Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classificationcited by 1
  16. 2022Robust Smart Home Face Recognition under Starving Federated Datacited by 0
  17. 2024AED-PADA:Improving Generalizability of Adversarial Example Detection via Principal Adversarial Domain Adaptationcited by 0
  18. 2024Active Fake: DeepFake Camouflagecited by 0
  19. 2025RAT: Boosting Misclassification Detection Ability without Extra Datacited by 0
  20. 2025Sharpness-Aware Geometric Defense for Robust Out-Of-Distribution Detectioncited by 0
  21. 2025Learning Aligned Stability in Neural ODEs Reconciling Accuracy with Robustnesscited by 0