A Study of the Removability of Speaker-Adversarial Perturbations

Summary

This study examines whether speaker-adversarial perturbations, which mislead speaker recognition models, can be removed from speech entirely. The authors test three scenarios of attacker knowledge (ignorant, semi-informed, well-informed) across optimization-based and feedforward perturbation generators on the LibriSpeech dataset. They find perturbations are not eliminated in the ignorant or semi-informed cases, while feedforward perturbations are considerably reduced in the semi-informed case and nearly eliminated in the well-informed case, allowing restoration of the original speech.

Topics

• Adversarial machine learning

Related items

• InfoQCLR: A Plug-in Robustification Module via Quantization for Contrastive Learning in Self-Supervised Skeleton-Based Human Action RecognitionSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoDoes Target Alignment Mean Target Recovery? An Evidence-Ladder Study of Adversarial Claims on Contrastive EncodersSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoBRANCH: Bypassing Multi-Scanner AI GuardrailsSimilar attack · Arxiv (cs.CR + cs.CL + cs.LG)
• InfoDetecting Adversarial Images through Response Profiles of Vision-Language ModelsSimilar attack · Arxiv (cs.RO + cs.CV security)
• InfoGraphRectify: Graph-Based Transfer of Adversarial Example Detectors Across Neural NetworksSimilar attack · Arxiv (cs.RO + cs.CV security)