# SSCNets: Robustifying DNNs using Secure Selective Convolutional Filters

arXiv: https://arxiv.org/abs/1811.01443 · HTML: https://mlsanity.com/paper/1811.01443/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Nov 2018.

## Built on by (most cited first, 4 of 4)

- [Adversarially Guided Stateful Defense Against Backdoor Attacks in Federated Deep Learning](https://mlsanity.com/paper/2410.11205/) (2024)
- [Exploiting Vulnerabilities in Deep Neural Networks: Adversarial and Fault-Injection Attacks](https://mlsanity.com/paper/2105.03251/) (2021)
- [Secure and Trustworthy Artificial Intelligence-Extended Reality (AI-XR) for Metaverses](https://mlsanity.com/paper/2210.13289/) (2022)
- [Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models](https://mlsanity.com/paper/2303.02669/) (2023)

## Abstract (arXiv)

In this paper, we introduce a novel technique based on the Secure Selective Convolutional (SSC) techniques in the training loop that increases the robustness of a given DNN by allowing it to learn the data distribution based on the important edges in the input image. We validate our technique on Convolutional DNNs against the state-of-the-art attacks from the open-source Cleverhans library using the MNIST, the CIFAR-10, and the CIFAR-100 datasets. Our experimental results show that the attack success rate, as well as the imperceptibility of the adversarial images, can be significantly reduced by adding effective pre-processing functions, i.e., Sobel filtering.