Georgia Institute of Technology
Synthetic Speech Attacks Against Voice Assistants and Defenses
Abstract
dc:description.abstractVoice assistants have become increasingly prevalent in both home and enterprise environments, offering natural and convenient ways to interact with computing devices. However, this increasing adoption has also introduced new security vulnerabilities. This dissertation investigates three critical security aspects of voice assistant systems. First, we demonstrate that attackers can synthesize malicious commands using limited, unrelated speech samples to bypass speaker profile matching mechanisms, achieving high success rates even with a lightweight unit-selection synthesis technique. Second, we show how voice assistants can be exploited as covert channels for data exfiltration from compromised computers, characterizing the achievable data rates and reliability under various conditions. Third, we develop a novel liveness detection method based on harmonic distortion analysis, which leverages physical characteristics of audio reproduction systems to effectively distinguish between live and attack command speech in a threat model where the attacker remotely targets the voice assistant by transmitting the command via a compromised device speaker. Through extensive empirical evaluation, we demonstrate the feasibility of these attacks and the effectiveness of our proposed defense mechanism. Our findings highlight significant security challenges in current voice assistant systems while providing practical approaches for enhancing their security. This research contributes to both the understanding of voice assistant vulnerabilities and the development of robust countermeasures.
Degree
thesis:*- Level thesis:degree_level
- Doctoral
- Department dc:contributor.department
- Computer Science
- Grantor dc:publisher
- Georgia Institute of Technology
- Year dc:date.issued
- 2024
Author and committee
dc:creator, dc:contributor.*- Author dc:creator
-
- He, Zhengxian
- Advisor dc:contributor.advisor
-
- Ahamad, Mustaque
- Committee members dc:contributor.committeemember
-
- Boldyreva, Alexandra
- Zonouz, Saman
- Li, Frank
- Kundu, Ashish
Subjects
dc:subject × 7Rights
- Language dc:language.iso
- en_US
Identifiers
dc:identifier.*- Handle dc:identifier.uri
- https://hdl.handle.net/1853/81477