前言
本篇同样是之前调研内容的整理,于 2020 年 9 月 29 日记录。
2020 年的 USENIX Security 中 Voice and Speech 共有 5 篇论文如下。
[1]Z. Guo, Z. Lin, P. Li, and K. Chen, “SkillExplorer: Understanding the Behavior of Skills in Large Scale,” in 29th USENIX Security Symposium (USENIX Security 20), Aug. 2020, pp. 2649–2666, [Online]. Available: https://www.usenix.org/conference/usenixsecurity20/presentation/guo.
[2]T. Sugawara, B. Cyr, S. Rampazzi, D. Genkin, and K. Fu, “Light Commands: Laser-Based Audio Injection Attacks on Voice-Controllable Systems,” in 29th USENIX Security Symposium (USENIX Security 20), Aug. 2020, pp. 2631–2648, [Online]. Available: https://www.usenix.org/conference/usenixsecurity20/presentation/sugawara.
[3]Y. Chen et al., “DevilWhisper: A General Approach for Physical Adversarial Attacks against Commercial Black-box Speech Recognition Devices,” in 29th USENIX Security Symposium (USENIX Security 20), Aug. 2020, pp. 2667–2684, [Online]. Available: https://www.usenix.org/conference/usenixsecurity20/presentation/chen-yuxuan.
[4]M. E. Ahmed, I.-Y. Kwak, J. H. Huh, I. Kim, T. Oh, and H. Kim, “Void: A fast and light voice liveness detection system,” in 29th USENIX Security Symposium (USENIX Security 20), Aug. 2020, pp. 2685–2702, [Online]. Available: https://www.usenix.org/conference/usenixsecurity20/presentation/ahmed-muhammad.
[5]S. Ahmed, A. R. Chowdhury, K. Fawaz, and P. Ramanathan, “Preech: A System for Privacy-Preserving Speech Transcription,” in 29th USENIX Security Symposium (USENIX Security 20), Aug. 2020, pp. 2703–2720, [Online]. Available: https://www.usenix.org/conference/usenixsecurity20/presentation/ahmed-shimaa.
下面依次简要说明内容。