Nonsense attacks on Google Assistant and missense attacks on Amazon Alexa
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 apparentl...
| Main Authors: | , , |
|---|---|
| 格式: | Conference item |
| 出版: |
SciTePress
2019
|
| _version_ | 1826263139825483776 |
|---|---|
| author | Bispham, M Agrafiotis, I Goldsmith, M |
| author_facet | Bispham, M Agrafiotis, I Goldsmith, M |
| author_sort | Bispham, M |
| collection | OXFORD |
| description | 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. |
| first_indexed | 2024-03-06T19:46:57Z |
| format | Conference item |
| id | oxford-uuid:22a26ee8-9c36-4dda-878f-09f3ec32cc9c |
| institution | University of Oxford |
| last_indexed | 2024-03-06T19:46:57Z |
| publishDate | 2019 |
| publisher | SciTePress |
| record_format | dspace |
| spelling | oxford-uuid:22a26ee8-9c36-4dda-878f-09f3ec32cc9c2022-03-26T11:39:50ZNonsense attacks on Google Assistant and missense attacks on Amazon AlexaConference itemhttp://purl.org/coar/resource_type/c_5794uuid:22a26ee8-9c36-4dda-878f-09f3ec32cc9cSymplectic Elements at OxfordSciTePress2019Bispham, MAgrafiotis, IGoldsmith, MThis 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. |
| spellingShingle | Bispham, M Agrafiotis, I Goldsmith, M Nonsense attacks on Google Assistant and missense attacks on Amazon Alexa |
| title | Nonsense attacks on Google Assistant and missense attacks on Amazon Alexa |
| title_full | Nonsense attacks on Google Assistant and missense attacks on Amazon Alexa |
| title_fullStr | Nonsense attacks on Google Assistant and missense attacks on Amazon Alexa |
| title_full_unstemmed | Nonsense attacks on Google Assistant and missense attacks on Amazon Alexa |
| title_short | Nonsense attacks on Google Assistant and missense attacks on Amazon Alexa |
| title_sort | nonsense attacks on google assistant and missense attacks on amazon alexa |
| work_keys_str_mv | AT bisphamm nonsenseattacksongoogleassistantandmissenseattacksonamazonalexa AT agrafiotisi nonsenseattacksongoogleassistantandmissenseattacksonamazonalexa AT goldsmithm nonsenseattacksongoogleassistantandmissenseattacksonamazonalexa |