The growing network of interconnected devices known as the Internet of Things (IoT) promises to make humans more productive, efficient, and healthy using sensors that monitor everything from the number of steps we take each day to the temperature of our homes. But a major concern about the IoT is its lack of security measures, which creates anxiety about exposing our most personal data.
The problem becomes even more complicated when households deploy multiple smart devices—all capable of being hacked and giving up sensitive data. There is a recent trend in the IoT world that many third-party, commercial IoT devices are now becoming voice enabled by using the APIs offered by the voice-controlled home-hub devices like Echo or Google Home. Because these home-hubs enable actuation and control of real-world entities, a potential danger is that they can be activated by false commands (e.g., sounds from a TV) and/or unauthorized commands (e.g., an outsider commands someone’s home hub to control his home appliances, places a large purchase on his Amazon account, or calls an Uber driver). A careful scrutiny of voice commands is therefore a necessity to ensure safety and security.
In this webinar, Nirjon discusses his research on the ‘overhearing’ problem of acoustic sensing devices and development of a system that mitigates personal or contextual information leakage due to the presence of unwanted sound sources in the acoustic environment.