Abstract:The nonuniform and growing impact of adversarial noise across the layers of deep neural networks has been used in the literature, without a formal mathematical justification, to detect adversarial inputs and improve robustness. In this work, we study this phenomenon in detail and present a formal adversarial noise amplification theorem. We specify a set of sufficient conditions under which the adversarial noise amplification is mathematically guaranteed. Based on theoretical observations, we propose a novel training methodology with a custom spectral loss function and a specific architectural design to enhance the amplification signal for detecting adversarial data. Finally, we introduce a new, lightweight detection mechanism that leverages the enhanced amplification signal and operates entirely at inference time. To validate our approach, we demonstrate the detector's efficacy against both state-of-the-art attacks and a purpose-built adaptive attack, confirming that enhanced amplification can serve as a robust and reliable signal for adversarial defense.
| Subjects: | Machine Learning (cs.LG); Cryptography and Security (cs.CR) |
| Cite as: | arXiv:2605.02109 [cs.LG] |
| (or arXiv:2605.02109v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2605.02109 arXiv-issued DOI via DataCite (pending registration) |
From: Furkan Mumcu [view email]
[v1]
Mon, 4 May 2026 00:08:05 UTC (641 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。