A safe collaborative chatbot for smart home assistants

Merav Chkroun, Amos Azaria

Research output: Contribution to journalArticlepeer-review

3 Scopus citations


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.

Original languageEnglish
Article number6641
Issue number19
StatePublished - 1 Oct 2021


  • Collaborative smart home assistants
  • Human–agent interaction
  • Mitigating offensive behavior
  • Smart environments


Dive into the research topics of 'A safe collaborative chatbot for smart home assistants'. Together they form a unique fingerprint.

Cite this