# Super-Efficient Super Resolution for Fast Adversarial Defense at the Edge

arXiv: https://arxiv.org/abs/2112.14340 · HTML: https://mlsanity.com/paper/2112.14340/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 27 references that are in the map.
- First posted on arXiv 29 Dec 2021.

## Builds on (most cited first, 25 of 25)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [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)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [MobileNetV2: Inverted Residuals and Linear Bottlenecks](https://mlsanity.com/paper/1801.04381/) (2018)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [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)
- [Fast is better than free: Revisiting adversarial training](https://mlsanity.com/paper/2001.03994/) (2020)
- [Improving Transferability of Adversarial Examples with Input Diversity](https://mlsanity.com/paper/1803.06978/) (2018)
- [Countering Adversarial Images using Input Transformations](https://mlsanity.com/paper/1711.00117/) (2017)
- [Accelerating the Super-Resolution Convolutional Neural Network](https://mlsanity.com/paper/1608.00367/) (2016)
- [Mitigating Adversarial Effects Through Randomization](https://mlsanity.com/paper/1711.01991/) (2017)
- [Data-Free Quantization Through Weight Equalization and Bias Correction](https://mlsanity.com/paper/1906.04721/) (2019)
- [Feature Denoising for Improving Adversarial Robustness](https://mlsanity.com/paper/1812.03411/) (2018)
- [On the Optimization of Deep Networks: Implicit Acceleration by Overparameterization](https://mlsanity.com/paper/1802.06509/) (2018)
- [Torchattacks: A PyTorch Repository for Adversarial Attacks](https://mlsanity.com/paper/2010.01950/) (2020)
- [Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compression](https://mlsanity.com/paper/1705.02900/) (2017)
- [Deflecting Adversarial Attacks with Pixel Deflection](https://mlsanity.com/paper/1801.08926/) (2018)
- [Image Super-Resolution as a Defense Against Adversarial Attacks](https://mlsanity.com/paper/1901.01677/) (2019)
- [ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks](https://mlsanity.com/paper/1811.10495/) (2018)
- [Dream Distillation: A Data-Independent Model Compression Framework](https://mlsanity.com/paper/1905.07072/) (2019)
- [Collapsible Linear Blocks for Super-Efficient Super Resolution](https://mlsanity.com/paper/2103.09404/) (2021)
- [BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Mining](https://mlsanity.com/paper/2109.14707/) (2021)

## Built on by (most cited first, 2 of 2)

- [PixLift: Accelerating Web Browsing via AI Upscaling](https://mlsanity.com/paper/2502.08995/) (2025)
- [Quaternion-Hadamard Network: A Novel Defense Against Adversarial Attacks with a New Dataset](https://mlsanity.com/paper/2502.10452/) (2025)

## Abstract (arXiv)

Autonomous systems are highly vulnerable to a variety of adversarial attacks on Deep Neural Networks (DNNs). Training-free model-agnostic defenses have recently gained popularity due to their speed, ease of deployment, and ability to work across many DNNs. To this end, a new technique has emerged for mitigating attacks on image classification DNNs, namely, preprocessing adversarial images using super resolution -- upscaling low-quality inputs into high-resolution images. This defense requires running both image classifiers and super resolution models on constrained autonomous systems. However, super resolution incurs a heavy computational cost. Therefore, in this paper, we investigate the following question: Does the robustness of image classifiers suffer if we use tiny super resolution models? To answer this, we first review a recent work called Super-Efficient Super Resolution (SESR) that achieves similar or better image quality than prior art while requiring 2x to 330x fewer Multiply-Accumulate (MAC) operations. We demonstrate that despite being orders of magnitude smaller than existing models, SESR achieves the same level of robustness as significantly larger networks. Finally, we estimate end-to-end performance of super resolution-based defenses on a commercial Arm Ethos-U55 micro-NPU. Our findings show that SESR achieves nearly 3x higher FPS than a baseline while achieving similar robustness.