Hear "No Evil", See "Kenansville": Efficient and Transferable Black-Box Attacks on Speech Recognition and Voice Identification Systems

• Published in: Proceedings - IEEE Symposium on Security and Privacy pp. 712 - 729
• Main Authors: Abdullah, Hadi, Rahman, Muhammad Sajidur, Garcia, Washington, Warren, Kevin, Yadav, Anurag Swarnim, Shrimpton, Tom, Traynor, Patrick
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.05.2021
• Subjects: Feature extraction; Force; Perturbation methods; Pipelines; Privacy; Robustness; Training

Automatic speech recognition and voice identification systems are being deployed in a wide array of applications, from providing control mechanisms to devices lacking traditional interfaces, to the automatic transcription of conversations and authentication of users. Many of these applications have...