Intelligent Virtual Assistants (IVAs) have opened up a new world of convenience in home and work ecosystems. Waking up in the morning and finding out, with a simple question, how the weather is or what is your schedule, completing your shopping list with a simple verbal request. IVA are also integrated and connected with other IoT smart home devices, we can ask to increase the temperature in the apartment, to prepare a coffee, show the baby camera, or open the garage door. This rapid expansion of IVA is a game changer with good and bad outcomes. Gartner predicts that the IVA market will increase to over 2.1BN by 2020. However, it appears that as we surround ourselves with more and more IVA devices, more and more news reports are delivering stories that are raising concerns regarding the reliability and trustworthiness of such IVAs. Such as our parrot is adding items in our shopping list, kindergartener accidentally ordering pricey toy, IVA is calling police without user interaction.
In this presentation we will discuss the IVA core architectures and the security and privacy concerns raised by their integration into home and work environments. We would employ statistical methods to ‘fingerprint’ IoT devices including IVA and would identify device state such as active, muted, and idle. We would discuss network traffic similarity analysis between IoT devices in smart home, and their link and communication patterns. The questions that are addressed in this presentation are:
- Can we identify the IoT devices in our home network by looking at the traffic?
- Is the network traffic similar among the IoT devices from the same manufacturer?
- Can we discover the communication pattern between devices by looking at the traffic?
This presentation will conclude with a brief discussion of our future research focused on leveraging the IoT device fingerprinting approach to identify malicious behavior or deviations from normal behavior that may raise security concerns.
The presentation session is organized in five parts each consist of lecture and interactive sections:
- Introduction to IVA and Smart Home IoT networks
- Architecture of IVAs (Alexa, Google assistant, Siri, Cortana)
- Security and privacy vulnerabilities scenarios
- Demonstrating of practical example – ML code and real-world data
- Conclusion
You need this ticket from Eventbrite to sign up:
Applied Machine Learning Conference.