# HyperNetworks with statistical filtering for defending adversarial examples

arXiv: https://arxiv.org/abs/1711.01791 · HTML: https://mlsanity.com/paper/1711.01791/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 Nov 2017.

## Built on by (most cited first, 9 of 9)

- [A Brief Review of Hypernetworks in Deep Learning](https://mlsanity.com/paper/2306.06955/) (2023)
- [Recomposing the Reinforcement Learning Building Blocks with Hypernetworks](https://mlsanity.com/paper/2106.06842/) (2021)
- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Principled Weight Initialization for Hypernetworks](https://mlsanity.com/paper/2312.08399/) (2023)
- [Amortized In-Context Bayesian Posterior Estimation](https://mlsanity.com/paper/2502.06601/) (2025)
- [Dynamic Inter-treatment Information Sharing for Individualized Treatment Effects Estimation](https://mlsanity.com/paper/2305.15984/) (2023)
- [Domain Generalization Deep Graph Transformation](https://mlsanity.com/paper/2305.11389/) (2023)
- [Individualised Treatment Effects Estimation with Composite Treatments and Composite Outcomes](https://mlsanity.com/paper/2502.08282/) (2025)
- [NeuMoSync: End-to-End Neuromodulatory Control for Plasticity and Adaptability in Continual Learning](https://mlsanity.com/paper/2608.04358/) (2026)

## Abstract (arXiv)

Deep learning algorithms have been known to be vulnerable to adversarial perturbations in various tasks such as image classification. This problem was addressed by employing several defense methods for detection and rejection of particular types of attacks. However, training and manipulating networks according to particular defense schemes increases computational complexity of the learning algorithms. In this work, we propose a simple yet effective method to improve robustness of convolutional neural networks (CNNs) to adversarial attacks by using data dependent adaptive convolution kernels. To this end, we propose a new type of HyperNetwork in order to employ statistical properties of input data and features for computation of statistical adaptive maps. Then, we filter convolution weights of CNNs with the learned statistical maps to compute dynamic kernels. Thereby, weights and kernels are collectively optimized for learning of image classification models robust to adversarial attacks without employment of additional target detection and rejection algorithms. We empirically demonstrate that the proposed method enables CNNs to spontaneously defend against different types of attacks, e.g. attacks generated by Gaussian noise, fast gradient sign methods (Goodfellow et al., 2014) and a black-box attack(Narodytska & Kasiviswanathan, 2016).