构建首个大规模语音验证对抗攻击数据集并提出高效防御方法。
Over-the-Air Adversarial Attack Detection: from Datasets to Defenses
- 构建包含628万样本的AdvSV 2.0数据集，覆盖OTL与OTA场景。
- 新攻击方法使对抗攻击威力更强，威胁更大。
- 提出CODA-OCC防御模型，误报率仅11.2%，性能领先。
自动说话人验证（ASV）系统广泛用于语音身份认证，但近年来暴露于线上（OTL）和空中（OTA）对抗攻击。尽管已有多种检测方法，因缺乏全面数据集而未充分验证。为此，我们构建了AdvSV 2.0数据集，包含628万样本，总时长达800小时，涵盖经典对抗攻击算法、ASV系统及OTL/OTA双重场景。此外，提出基于神经重放模拟器（NRS）的新攻击方法，显著增强对抗性OTA攻击效果。为应对攻击，提出一种在单类分类框架下的对比学习防御方法CODA-OCC。实验表明，该方法在AdvSV 2.0上实现EER为11.2%、AUC达0.95，优于多个先进检测方法。
原文摘要 · Abstract (English)
Automatic Speaker Verification (ASV) systems can be used for voice-enabled applications for identity verification. However, recent studies have exposed these systems' vulnerabilities to both over-the-line (OTL) and over-the-air (OTA) adversarial attacks. Although various detection methods have been proposed to counter these threats, they have not been thoroughly tested due to the lack of a comprehensive data set. To address this gap, we developed the AdvSV 2.0 dataset, which contains 628k samples with a total duration of 800 hours. This dataset incorporates classical adversarial attack algorithms, ASV systems, and encompasses both OTL and OTA scenarios. Furthermore, we introduce a novel adversarial attack method based on a Neural Replay Simulator (NRS), which enhances the potency of adversarial OTA attacks, thereby presenting a greater threat to ASV systems. To defend against these attacks, we propose CODA-OCC, a contrastive learning approach within the one-class classification framework. Experimental results show that CODA-OCC achieves an EER of 11.2% and an AUC of 0.95 on the AdvSV 2.0 dataset, outperforming several state-of-the-art detection methods.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。