mlsanityData to 7 Oct 2026

On the Robustness of the CVPR 2018 White-Box Adversarial Example Defenses

arXiv 1804.03286 ↗First posted 10 Apr 2018cs.CV cs.CR cs.LGcited by 40

Not on the map. Why?

Abstract (arXiv)

Neural networks are known to be vulnerable to adversarial examples. In this note, we evaluate the two white-box defenses that appeared at CVPR 2018 and find they are ineffective: when applying existing techniques, we can reduce the accuracy of the defended models to 0%.

Key facts. Cited by 40 papers in the map (data through 7 Oct 2026). First posted on arXiv 10 Apr 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 7; 2023: 4; 2024: 9; 2025: 2; 2026: 1.

40 papers.

Sort:

  1. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  2. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  3. 2021Intriguing Properties of Input-dependent Randomized Smoothingcited by 24
  4. 2023Towards Viewpoint-Invariant Visual Recognition via Adversarial Trainingcited by 19
  5. 2021Attack to Fool and Explain Deep Networkscited by 17
  6. 2021Towards Understanding Adversarial Robustness of Optical Flow Networkscited by 15
  7. 2021On Robustness of Neural Semantic Parserscited by 14
  8. 2022Improving Robustness by Enhancing Weak Subnetscited by 12
  9. 2021Responsible and Regulatory Conform Machine Learning for Medicine: A Survey of Challenges and Solutionscited by 7
  10. 2021Integer-arithmetic-only Certified Robustness for Quantized Neural Networkscited by 7
  11. 2023Improving Viewpoint Robustness for Visual Recognition via Adversarial Trainingcited by 7
  12. 2025Towards the Worst-case Robustness of Large Language Modelscited by 7
28 more
  1. 2021Selection of Source Images Heavily Influences the Effectiveness of Adversarial Attackscited by 6
  2. 2024FedCCL: Federated Dual-Clustered Feature Contrast Under Domain Heterogeneitycited by 5
  3. 2021Constrained Gradient Descent: A Powerful and Principled Evasion Attack Against Neural Networkscited by 4
  4. 2022Reverse Engineering ℓp attacks: A block-sparse optimization approach with recovery guaranteescited by 4
  5. 2022General Adversarial Defense Against Black-box Attacks via Pixel Level and Feature Level Distribution Alignmentscited by 4
  6. 2024Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningcited by 4
  7. 2024Logit Calibration and Feature Contrast for Robust Federated Learning on Non-IID Datacited by 4
  8. 2024AMA-LSTM: Pioneering Robust and Fair Financial Audio Analysis for Stock Volatility Predictioncited by 4
  9. 2021Improving White-box Robustness of Pre-processing Defenses via Joint Adversarial Trainingcited by 3
  10. 2021Mitigating Black-Box Adversarial Attacks via Output Noise Perturbationcited by 3
  11. 2022AdAUC: End-to-end Adversarial AUC Optimization Against Long-tail Problemscited by 3
  12. 2023PEARL: Preprocessing Enhanced Adversarial Robust Learning of Image Deraining for Semantic Segmentationcited by 3
  13. 2021Learning Defense Transformers for Counterattacking Adversarial Examplescited by 2
  14. 2021Simpler Certified Radius Maximization by Propagating Covariancescited by 2
  15. 2021Saliency Diversified Deep Ensemble for Robustness to Adversariescited by 2
  16. 2023Adversarial Attacks on Image Classification Models: Analysis and Defensecited by 2
  17. 2024Federated Hybrid Training and Self-Adversarial Distillation: Towards Robust Edge Networkscited by 2
  18. 2021Resilience from Diversity: Population-based approach to harden models against adversarial attackscited by 1
  19. 2021Denoised Internal Models: a Brain-Inspired Autoencoder against Adversarial Attackscited by 1
  20. 2022Robust Transferable Feature Extractors: Learning to Defend Pre-Trained Networks Against White Box Adversariescited by 1
  21. 2022DE-CROP: Data-efficient Certified Robustness for Pretrained Classifierscited by 1
  22. 2024Certified PEFTSmoothing: Parameter-Efficient Fine-Tuning with Randomized Smoothingcited by 1
  23. 2024OTAD: An Optimal Transport-Induced Robust Model for Agnostic Adversarial Attackcited by 1
  24. 2024ARQ: A Mixed-Precision Quantization Framework for Accurate and Certifiably Robust DNNscited by 1
  25. 2025Towards Communication-Efficient Adversarial Federated Learning for Robust Edge Intelligencecited by 1
  26. 2022Adversarial Defense via Image Denoising with Chaotic Encryptioncited by 0
  27. 2024Distributional Adversarial Losscited by 0
  28. 2026Adversarially Robust PAC Learning with Optimal VC Ratescited by 0