English(EN) The Perceived Fragility of Explanations in Audio Models: Manipulation of Attribution with Unchanged Predictions

音频深度伪造模型解释被发现存在脆弱性

作者 PulseAugur 编辑部 · [2 个来源] · 2026-06-12 13:58

研究人员已经证明，音频深度伪造检测模型的解释是可以被操纵的。通过引入不易察觉的扰动，攻击者可以在不改变音频片段是否为深度伪造的最终预测的情况下，改变模型的归因热图。这种漏洞在各种最先进的架构上进行了测试，突显了当前音频分析可解释性方法的潜在弱点。 AI

影响揭示了人工智能模型解释中的一个漏洞，可能影响音频深度伪造检测系统的信任和安全。

排序理由该集群包含一篇详细介绍人工智能模型可解释性研究成果的学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Research; 该集群包含一篇详细介绍人工智能模型可解释性研究成果的学术论文。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 118 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

arXiv cs.AI TIER_1 English(EN) · Piotr Kit{\l}owski, Dominik Wi\k{a}cek, Mateusz Modrzejewski · 2026-06-15 04:00

音频模型解释的感知脆弱性：在预测不变的情况下操纵归因

arXiv:2606.14466v1 Announce Type: cross Abstract: This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection. While previous work on explanation manipulation focused on images using standard $L_p$ metrics, we introduce a psychoacoustic frame…
arXiv cs.AI TIER_1 English(EN) · Mateusz Modrzejewski · 2026-06-12 13:58

音频模型解释的感知脆弱性：在预测不变的情况下操纵归因

This paper investigates the fragility of post-hoc explanation methods in audio deepfake detection. While previous work on explanation manipulation focused on images using standard $L_p$ metrics, we introduce a psychoacoustic framework that optimizes inaudible perturbations to dec…