TU Darmstadt / ULB / TUbiblio

Alexa Lied to Me: Skill-based Man-in-the-Middle Attacks on Virtual Assistants

Mitev, Richard and Miettinen, Markus and Sadeghi, Ahmad-Reza (2019):
Alexa Lied to Me: Skill-based Man-in-the-Middle Attacks on Virtual Assistants.
ACM, In: ASIACCS 2019, Auckland, New Zealand, Juli 2019, DOI: 10.1145/3321705.3329842,
[Online-Edition: https://tuprints.ulb.tu-darmstadt.de/8689],
[Conference or Workshop Item]

Abstract

Voice-based virtual personal assistants such as Amazon’s Alexa or Google Assistant have become highly popular and are used for diverse daily tasks ranging from querying on-line information, shopping, smart home control and a variety of enterprise application scenarios. Capabilities of virtual assistants can be enhanced with so-called Skills , i.e., programmatic extensions that allow thirdparty providers to integrate their services with the respective voice assistant.

In this paper, we show that specially crafted malicious Skills can use the seemingly limited Skill interaction model to cause harm. We present novel man-in-the-middle attacks against benign Skills and Virtual Assistant functionalities. Our attack uses loopholes in the Skill interface to redirect a victim’s voice input to a malicious Skill, thereby hijacking the conversation between Alexa and the victim. To the best of our knowledge this is the first man-in-the-middle attack targeting the Skill ecosystem. We present the design of our attack and demonstrate its feasibility based on a proof-of-concept implementation attacking the Alexa Skills of a smart lock as well as a home security system.

Item Type: Conference or Workshop Item
Erschienen: 2019
Creators: Mitev, Richard and Miettinen, Markus and Sadeghi, Ahmad-Reza
Title: Alexa Lied to Me: Skill-based Man-in-the-Middle Attacks on Virtual Assistants
Language: English
Abstract:

Voice-based virtual personal assistants such as Amazon’s Alexa or Google Assistant have become highly popular and are used for diverse daily tasks ranging from querying on-line information, shopping, smart home control and a variety of enterprise application scenarios. Capabilities of virtual assistants can be enhanced with so-called Skills , i.e., programmatic extensions that allow thirdparty providers to integrate their services with the respective voice assistant.

In this paper, we show that specially crafted malicious Skills can use the seemingly limited Skill interaction model to cause harm. We present novel man-in-the-middle attacks against benign Skills and Virtual Assistant functionalities. Our attack uses loopholes in the Skill interface to redirect a victim’s voice input to a malicious Skill, thereby hijacking the conversation between Alexa and the victim. To the best of our knowledge this is the first man-in-the-middle attack targeting the Skill ecosystem. We present the design of our attack and demonstrate its feasibility based on a proof-of-concept implementation attacking the Alexa Skills of a smart lock as well as a home security system.

Journal or Publication Title: Proceedings of the 2019 on Asia Conference on Computer and Communications Security
Publisher: ACM
Divisions: 20 Department of Computer Science
20 Department of Computer Science > Security, Usability and Society
Event Title: ASIACCS 2019
Event Location: Auckland, New Zealand
Event Dates: Juli 2019
Date Deposited: 11 Aug 2019 19:55
DOI: 10.1145/3321705.3329842
Official URL: https://tuprints.ulb.tu-darmstadt.de/8689
URN: urn:nbn:de:tuda-tuprints-86890
Export:

Optionen (nur für Redakteure)

View Item View Item