# Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks

Source: [Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks](<https://www.sota2.com/research/paper/691414a62828b7cc6937ed01>)

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

Data updated: 2025-11-13T05:03:13.274Z

Authors: Aja Khanal, Ahmed Faid, Apurva Narayan

Published: 2025-11-11T02:12:35.000Z

## Abstract

Deep learning vision systems are increasingly deployed in safety-critical domains such as healthcare, yet they remain vulnerable to small adversarial patches that can trigger misclassifications. Most existing defenses assume a single patch and fail when multiple localized disruptions occur, the type of scenario adversaries and real-world artifacts often exploit. We propose Filtered-ViT, a new vision transformer architecture that integrates SMART Vector Median Filtering (SMART-VMF), a spatially adaptive, multi-scale, robustness-aware mechanism that enables selective suppression of corrupted regions while preserving semantic detail. On ImageNet with LaVAN multi-patch attacks, Filtered-ViT achieves 79.8% clean accuracy and 46.3% robust accuracy under four simultaneous 1\\% patches, outperforming existing defenses. Beyond synthetic benchmarks, a real-world case study on radiographic medical imagery shows that Filtered-ViT mitigates natural artifacts such as occlusions and scanner noise without degrading diagnostic content. This establishes Filtered-ViT as the first transformer to demonstrate unified robustness against both adversarial and naturally occurring patch-like disruptions, charting a path toward reliable vision systems in truly high-stakes environments.

## 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/2511.07755>)

[PDF](<https://arxiv.org/pdf/2511.07755.pdf>)
