2022
DOI: 10.1007/978-981-16-9480-6_4
|View full text |Cite
|
Sign up to set email alerts
|

Attack on AI Smart Speakers with a Laser Beam

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
0
0

Year Published

2023
2023
2023
2023

Publication Types

Select...
1

Relationship

1
0

Authors

Journals

citations
Cited by 1 publication
(2 citation statements)
references
References 6 publications
0
0
0
Order By: Relevance
“…Next, the attacker needs a plan to replay the recorded sound commands. We started with the commands listed below in Table 5 [39], which shows each command with its individual functions, from setting the voice assistant to make them inaudible to the owner, to trying to purchase something in online stores. To do that we used a typical smartphone that was accompanied by a Neoteck NTK059 headphone amplifier (it costs only USD 30 online).…”
Section: Sound Source and Test Resultsmentioning
confidence: 99%
See 1 more Smart Citation
“…Next, the attacker needs a plan to replay the recorded sound commands. We started with the commands listed below in Table 5 [39], which shows each command with its individual functions, from setting the voice assistant to make them inaudible to the owner, to trying to purchase something in online stores. To do that we used a typical smartphone that was accompanied by a Neoteck NTK059 headphone amplifier (it costs only USD 30 online).…”
Section: Sound Source and Test Resultsmentioning
confidence: 99%
“…The most striking example of this kind is DolphinAttack [15], which was also aimed at deceiving voice assistants through "inaudible" ultrasonic commands. We can also recall similar studies of BackDoor [19] and LipRead [21], as well as a similar attack technique, Light Commands [33,46], which also allows us to silently issue commands to smart devices, but does not use ultrasound, and instead a laser for this. However, unfortunately, all these attacks require certain devices and work to be carried out on them.…”
Section: Attack Motivationmentioning
confidence: 93%