{"ID":2843090,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.07755","arxiv_id":"2511.07755","title":"Filtered-ViT: A Robust Defense Against Multiple Adversarial Patch Attacks","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.","short_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 adversa...","url_abs":"https://arxiv.org/abs/2511.07755","url_pdf":"https://arxiv.org/pdf/2511.07755v1","authors":"[\"Aja Khanal\",\"Ahmed Faid\",\"Apurva Narayan\"]","published":"2025-11-11T02:12:35Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Vision Transformer\",\"Transformer\"]","has_code":false}