# Robust Convolutional Neural Networks under Adversarial Noise

arXiv: https://arxiv.org/abs/1511.06306 · HTML: https://mlsanity.com/paper/1511.06306/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Nov 2015.

## Built on by (most cited first, 13 of 13)

- [Towards Trustworthy and Aligned Machine Learning: A Data-centric Survey with Causality Perspectives](https://mlsanity.com/paper/2307.16851/) (2023)
- [Uncertainty Quantification via Stable Distribution Propagation](https://mlsanity.com/paper/2402.08324/) (2024)
- [A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunities](https://mlsanity.com/paper/2210.08906/) (2022)
- [Benchmarking the Robustness of Instance Segmentation Models](https://mlsanity.com/paper/2109.01123/) (2021)
- [Attribution of Gradient Based Adversarial Attacks for Reverse Engineering of Deceptions](https://mlsanity.com/paper/2103.11002/) (2021)
- [Resisting Adversarial Attacks in Deep Neural Networks using Diverse Decision Boundaries](https://mlsanity.com/paper/2208.08697/) (2022)
- [Sampling-free Variational Inference for Neural Networks with Multiplicative Activation Noise](https://mlsanity.com/paper/2103.08497/) (2021)
- [An Introduction to Robust Graph Convolutional Networks](https://mlsanity.com/paper/2103.14807/) (2021)
- [Identifying and Exploiting Structures for Reliable Deep Learning](https://mlsanity.com/paper/2108.07083/) (2021)
- [Uncertainty Detection and Reduction in Neural Decoding of EEG Signals](https://mlsanity.com/paper/2201.00627/) (2021)
- [A study on the deviations in performance of FNNs and CNNs in the realm of grayscale adversarial images](https://mlsanity.com/paper/2209.08262/) (2022)
- [Single-shot Bayesian approximation for neural networks](https://mlsanity.com/paper/2308.12785/) (2023)
- [Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Them](https://mlsanity.com/paper/2401.11723/) (2024)

## Abstract (arXiv)

Recent studies have shown that Convolutional Neural Networks (CNNs) are vulnerable to a small perturbation of input called "adversarial examples". In this work, we propose a new feedforward CNN that improves robustness in the presence of adversarial noise. Our model uses stochastic additive noise added to the input image and to the CNN models. The proposed model operates in conjunction with a CNN trained with either standard or adversarial objective function. In particular, convolution, max-pooling, and ReLU layers are modified to benefit from the noise model. Our feedforward model is parameterized by only a mean and variance per pixel which simplifies computations and makes our method scalable to a deep architecture. From CIFAR-10 and ImageNet test, the proposed model outperforms other methods and the improvement is more evident for difficult classification tasks or stronger adversarial noise.