Nonsense attacks on Google Assistant and missense attacks on Amazon Alexa

Conference item

This paper presents novel attacks on voice-controlled digital assistants using nonsensical word sequences. We present the results of a small-scale experiment which demonstrates that it is possible for malicious actors to gain covert access to a voice-controlled system by hiding commands in apparently nonsensical sounds of which the meaning is opaque to humans. Several instances of nonsensical word sequences were identified which triggered a target command in a voice-controlled digital assistant, but which were incomprehensible to humans, as shown in tests with human experimental subjects. Our work confirms the potential for hiding malicious voice commands to voice-controlled digital assistants or other speech-controlled devices in speech sounds which are perceived by humans as nonsensical. This paper also develops a novel attack concept which involves gaining unauthorised access to a voice-controlled system using apparently unrelated utterances. We present the results of a proof-of-co ncept study showing that it is possible to trigger actions in a voice-controlled digital assistant using utterances which are accepted by the system as a target command despite having a different meaning to the command in terms of human understanding.

Authors: Bispham, M; Agrafiotis, I; Goldsmith, M

• Publication status: Published
• Peer review status: Peer reviewed
• Publisher: SciTePress
• Host title: Proceedings of the 5th International Conference on Information Systems Security and Privacy
• Journal: 5th International Conference on Information Systems Security and Privacy
• Volume: 1
• Pages: 75-87
• Publication date: 2019-03-14
• Acceptance date: 2018-12-01
• DOI: 10.5220/0007309500750087
• ISBN: 9789897583599
• Keywords: voice-controlled digital assistant; cyber security; human-computer interaction