mlsanityData to 7 Oct 2026

Adversarial Parameter Attack on Deep Neural Networks

arXiv 2203.10502 ↗First posted 20 Mar 2022cs.LG cs.CRcited by 6

Not on the map. Why?

Abstract (arXiv)

In this paper, a new parameter perturbation attack on DNNs, called adversarial parameter attack, is proposed, in which small perturbations to the parameters of the DNN are made such that the accuracy of the attacked DNN does not decrease much, but its robustness becomes much lower. The adversarial parameter attack is stronger than previous parameter perturbation attacks in that the attack is more difficult to be recognized by users and the attacked DNN gives a wrong label for any modified sample input with high probability. The existence of adversarial parameters is proved. For a DNN FTheta with the parameter set Theta satisfying certain conditions, it is shown that if the depth of the DNN is sufficiently large, then there exists an adversarial parameter set Thetaa for Theta such that the accuracy of FThetaa is equal to that of FTheta, but the robustness measure of FThetaa is smaller than any given bound. An effective training algorithm is given to compute adversarial parameters and numerical experiments are used to demonstrate that the algorithms are effective to produce high quality adversarial parameters.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 34 of its 58 references that are in the map. First posted on arXiv 20 Mar 2022.

Builds on

34 of 58 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Wide Residual Networkscited by 3,057
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  8. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  9. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  10. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  12. 2016Pruning Filters for Efficient ConvNetscited by 1,129
22 more
  1. 2015The Limitations of Deep Learning in Adversarial Settingscited by 784
  2. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  3. 2018Certified Defenses against Adversarial Examplescited by 305
  4. 2015Norm-Based Capacity Control in Neural Networkscited by 299
  5. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 234
  6. 2018Why do deep convolutional networks generalize so poorly to small image transformations?cited by 198
  7. 2017Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulationcited by 182
  8. 2017The Space of Transferable Adversarial Examplescited by 156
  9. 2018Are adversarial examples inevitable?cited by 113
  10. 2018On the importance of single directions for generalizationcited by 99
  11. 2016Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Unitscited by 86
  12. 2019On the Connection Between Adversarial Robustness and Saliency Map Interpretabilitycited by 80
  13. 2020Towards Robust Pattern Recognition: A Reviewcited by 31
  14. 2020Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruptioncited by 26
  15. 2019Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networkscited by 25
  16. 2021The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networkscited by 16
  17. 2020MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Anglescited by 15
  18. 2020On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systemscited by 13
  19. 2021The Feasibility and Inevitability of Stealth Attackscited by 12
  20. 2018DeepLaser: Practical Fault Attack on Deep Neural Networkscited by 3
  21. 2020Recent Advances in Understanding Adversarial Robustness of Deep Neural Networkscited by 3
  22. 2021Robust and Information-theoretically Safe Bias Classifier against Adversarial Attackscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 2; 2023: 0; 2024: 0; 2025: 2; 2026: 2.

6 papers.

  1. 2022Isometric 3D Adversarial Examples in the Physical Worldcited by 25
  2. 2025Topological derivative approach for deep neural network architecture adaptationcited by 2
  3. 2022Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Gamecited by 0
  4. 2025Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Abilitycited by 0
  5. 2026Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attackscited by 0
  6. 2026On the Effect of Bit-Level Parameter Perturbations in Machine Learning and Deep Learning Modelscited by 0