{"ID":2860769,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.02707","arxiv_id":"2510.02707","title":"A Statistical Method for Attack-Agnostic Adversarial Attack Detection with Compressive Sensing Comparison","abstract":"Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this work, we propose a statistical approach that establishes a detection baseline before a neural network's deployment, enabling effective real-time adversarial detection. We generate a metric of adversarial presence by comparing the behavior of a compressed/uncompressed neural network pair. Our method has been tested against state-of-the-art techniques, and it achieves near-perfect detection across a wide range of attack types. Moreover, it significantly reduces false positives, making it both reliable and practical for real-world applications.","short_abstract":"Adversarial attacks present a significant threat to modern machine learning systems. Yet, existing detection methods often lack the ability to detect unseen attacks or detect different attack types with a high level of accuracy. In this work, we propose a statistical approach that establishes a detection baseline befor...","url_abs":"https://arxiv.org/abs/2510.02707","url_pdf":"https://arxiv.org/pdf/2510.02707v1","authors":"[\"Chinthana Wimalasuriya\",\"Spyros Tragoudas\"]","published":"2025-10-03T04:05:20Z","proceeding":"cs.CR","tasks":"[\"cs.CR\",\"cs.CV\",\"cs.LG\",\"eess.IV\"]","methods":"[]","has_code":false}