# Adversarial Parameter Attack on Deep Neural Networks

arXiv: https://arxiv.org/abs/2203.10502 · HTML: https://mlsanity.com/paper/2203.10502/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 34 of its 58 references that are in the map.
- First posted on arXiv 20 Mar 2022.

## Builds on (most cited first, 30 of 34)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [Towards Evaluating the Robustness of Neural Networks](https://mlsanity.com/paper/1608.04644/) (2016)
- [Theoretically Principled Trade-off between Robustness and Accuracy](https://mlsanity.com/paper/1901.08573/) (2019)
- [Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks](https://mlsanity.com/paper/2003.01690/) (2020)
- [Certified Adversarial Robustness via Randomized Smoothing](https://mlsanity.com/paper/1902.02918/) (2019)
- [Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examples](https://mlsanity.com/paper/1802.00420/) (2018)
- [Pruning Filters for Efficient ConvNets](https://mlsanity.com/paper/1608.08710/) (2016)
- [The Limitations of Deep Learning in Adversarial Settings](https://mlsanity.com/paper/1511.07528/) (2015)
- [Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey](https://mlsanity.com/paper/1801.00553/) (2018)
- [Certified Defenses against Adversarial Examples](https://mlsanity.com/paper/1801.09344/) (2018)
- [Norm-Based Capacity Control in Neural Networks](https://mlsanity.com/paper/1503.00036/) (2015)
- [Adversarial Attacks and Defenses in Images, Graphs and Text: A Review](https://mlsanity.com/paper/1909.08072/) (2019)
- [Why do deep convolutional networks generalize so poorly to small image transformations?](https://mlsanity.com/paper/1805.12177/) (2018)
- [Formal Guarantees on the Robustness of a Classifier against Adversarial Manipulation](https://mlsanity.com/paper/1705.08475/) (2017)
- [The Space of Transferable Adversarial Examples](https://mlsanity.com/paper/1704.03453/) (2017)
- [Are adversarial examples inevitable?](https://mlsanity.com/paper/1809.02104/) (2018)
- [On the importance of single directions for generalization](https://mlsanity.com/paper/1803.06959/) (2018)
- [Understanding and Improving Convolutional Neural Networks via Concatenated Rectified Linear Units](https://mlsanity.com/paper/1603.05201/) (2016)
- [On the Connection Between Adversarial Robustness and Saliency Map Interpretability](https://mlsanity.com/paper/1905.04172/) (2019)
- [Towards Robust Pattern Recognition: A Review](https://mlsanity.com/paper/2006.06976/) (2020)
- [Fault Sneaking Attack: a Stealthy Framework for Misleading Deep Neural Networks](https://mlsanity.com/paper/1905.12032/) (2019)
- [Exploring the Vulnerability of Deep Neural Networks: A Study of Parameter Corruption](https://mlsanity.com/paper/2006.05620/) (2020)
- [The mathematics of adversarial attacks in AI -- Why deep learning is unstable despite the existence of stable neural networks](https://mlsanity.com/paper/2109.06098/) (2021)
- [MMA Regularization: Decorrelating Weights of Neural Networks by Maximizing the Minimal Angles](https://mlsanity.com/paper/2006.06527/) (2020)
- [On Adversarial Examples and Stealth Attacks in Artificial Intelligence Systems](https://mlsanity.com/paper/2004.04479/) (2020)

## Built on by (most cited first, 6 of 6)

- [Isometric 3D Adversarial Examples in the Physical World](https://mlsanity.com/paper/2210.15291/) (2022)
- [Topological derivative approach for deep neural network architecture adaptation](https://mlsanity.com/paper/2502.06885/) (2025)
- [Achieve Optimal Adversarial Accuracy for Adversarial Deep Learning using Stackelberg Game](https://mlsanity.com/paper/2207.08137/) (2022)
- [Generalizability of Neural Networks Minimizing Empirical Risk Based on Expressive Ability](https://mlsanity.com/paper/2503.04111/) (2025)
- [Toward a Generalized Defense Across Sparse, Continuous, and Structured Parameter Attacks](https://mlsanity.com/paper/2606.04317/) (2026)
- [On the Effect of Bit-Level Parameter Perturbations in Machine Learning and Deep Learning Models](https://mlsanity.com/paper/2609.26280/) (2026)

## 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.