# DSRNA: Differentiable Search of Robust Neural Architectures

Source: [DSRNA: Differentiable Search of Robust Neural Architectures](<https://www.sota2.com/research/paper/68fa68f71e209131cea1f61b>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T22:50:52.043Z

Authors: Ramtin Hosseini, Xingyi Yang, Pengtao Xie

Published: 2020-12-11T04:52:54.000Z

## Abstract

In deep learning applications, the architectures of deep neural networks are crucial in achieving high accuracy. Many methods have been proposed to search for high-performance neural architectures automatically. However, these searched architectures are prone to adversarial attacks. A small perturbation of the input data can render the architecture to change prediction outcomes significantly. To address this problem, we propose methods to perform differentiable search of robust neural architectures. In our methods, two differentiable metrics are defined to measure architectures' robustness, based on certified lower bound and Jacobian norm bound. Then we search for robust architectures by maximizing the robustness metrics. Different from previous approaches which aim to improve architectures' robustness in an implicit way: performing adversarial training and injecting random noise, our methods explicitly and directly maximize robustness metrics to harvest robust architectures. On CIFAR-10, ImageNet, and MNIST, we perform game-based evaluation and verification-based evaluation on the robustness of our methods. The experimental results show that our methods 1) are more robust to various norm-bound attacks than several robust NAS baselines; 2) are more accurate than baselines when there are no attacks; 3) have significantly higher certified lower bounds than baselines.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Adversarial Robust Image Classification on CIFAR-10 (test)](<https://www.sota2.com/research/sota/adversarial-robust-image-classification-on-cifar-10-test.md>): Image Classification; CIFAR-10 (test); Accuracy (Clean): 80.93.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2012.06122>)

[PDF](<https://arxiv.org/pdf/2012.06122.pdf>)
