# Test-time Detection and Repair of Adversarial Samples via Masked Autoencoder

Source: [Test-time Detection and Repair of Adversarial Samples via Masked Autoencoder](<https://www.sota2.com/research/paper/68fa6ef21e209131cea43171>)

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

Data updated: 2025-10-26T01:10:39.531Z

Authors: Yun-Yun Tsai, Ju-Chin Chao, Albert Wen, Zhaoyuan Yang, Chengzhi Mao, Tapan Shah, Junfeng Yang

Published: 2023-03-22T18:14:02.000Z

## Abstract

Training-time defenses, known as adversarial training, incur high training costs and do not generalize to unseen attacks. Test-time defenses solve these issues but most existing test-time defenses require adapting the model weights, therefore they do not work on frozen models and complicate model memory management. The only test-time defense that does not adapt model weights aims to adapt the input with self-supervision tasks. However, we empirically found these self-supervision tasks are not sensitive enough to detect adversarial attacks accurately. In this paper, we propose DRAM, a novel defense method to detect and repair adversarial samples at test time via Masked autoencoder (MAE). We demonstrate how to use MAE losses to build a Kolmogorov-Smirnov test to detect adversarial samples. Moreover, we use the MAE losses to calculate input reversal vectors that repair adversarial samples resulting from previously unseen attacks. Results on large-scale ImageNet dataset show that, compared to all detection baselines evaluated, DRAM achieves the best detection rate (82% on average) on all eight adversarial attacks evaluated. For attack repair, DRAM improves the robust accuracy by 6% ~ 41% for standard ResNet50 and 3% ~ 8% for robust ResNet50 compared with the baselines that use contrastive learning and rotation prediction.

## 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.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2303.12848>)

[PDF](<https://arxiv.org/pdf/2303.12848.pdf>)
