Abstract
Smart home assistants, which enable users to control home appliances and can be used for holding entertaining conversations, have become an inseparable part of many people’s homes. Recently, there have been many attempts to allow end-users to teach a home assistant new commands, responses, and rules, which can then be shared with a larger community. However, allowing end-users to teach an agent new responses, which are shared with a large community, opens the gate to malicious users, who can teach the agent inappropriate responses in order to promote their own business, products, or political views. In this paper, we present a platform that enables users to collaboratively teach a smart home assistant (or chatbot) responses using natural language. We present a method of collectively detecting malicious users and using the commands taught by the malicious users to further mitigate activity of future malicious users. We ran an experiment with 192 subjects and show the effectiveness of our platform.
Funder
Ministry of Science and Technology, Israel
Subject
Electrical and Electronic Engineering,Biochemistry,Instrumentation,Atomic and Molecular Physics, and Optics,Analytical Chemistry
Reference31 articles.
1. Global Smart Speakers Markets Report 2021: Amazon Alexa, Google Assistant, Siri, Cortana, Others-Market Is Expected to Reach $17.85 Billion in 2025 at a CAGR of 26%https://www.globenewswire.com/en/news-release/2021/05/24/2234471/28124/en/Global-Smart-Speakers-Markets-Report-2021-Amazon-Alexa-Google-Assistant-Siri-Cortana-Others-Market-is-Expected-to-Reach-17-85-Billion-in-2025-at-a-CAGR-of-26.html
2. Smart Speaker Market to Grow at 21% CAGR during 2020–2025https://www.counterpointresearch.com/smart-speaker-drivers/
3. A Survey of User-Centred Approaches for Smart Home Transfer Learning and New User Home Automation Adaptation
4. Instructable Intelligent Personal Agent;Azaria,2016
5. SUGILITE: Creating Multimodal Smartphone Automation by Demonstration;Li,2017
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献