Project Info

HomeGuard: Safeguarding User-Centric Privacy in Smart Homes using AI@Edge

Dong Chen

Project Goals and Description:

The Internet of Things (IoT)  and Edge Computing devices have been increasingly deployed in smart homes and buildings to automatically monitor and control their environments. Unfortunately, extensive recent research has shown that the Internet on-path external adversaries can infer and further fingerprint people's sensitive in-home activities by analyzing IoT network traffic traces. To address these issues, we design a new low-cost, distributed user-centric defense system---HomeGuard that enables people to leverage AI@Edge to regain the privacy leakage control of their IoT devices, while still permitting sophisticated IoT data analytics that is necessary for smart home and building automation.

More Information:

Grand Challenge: Secure cyberspace. [IPSN’21] PrivacyGuard: Enhancing Smart Home User Privacy. Keyang Yu, Qi Li, Dong Chen, Mohammad Rahmann, and Shiqiang Wang. In Proc. of the 20th ACM/IEEE International Conference on Information Processing in Sensor Networks, IPSN’21, May 18–21, 2021, Nashville, TN, USA. Acceptance Rate = 24.76%. [CNS’22] TrafficSpy: Disaggregating VPN-encrypted IoT Network Traffic for User Privacy Inference. Qi Li, Keyang Yu, Dong Chen, Mo Sha and Long Cheng. In Proc. of the 10th IEEE Conference on Communications and Network Security (CNS 2022), 3-5 October 2022, Austin, Texas, USA. Acceptance Rate = 35.25%.

Primary Contacts:

Dong Chen, | Keyang Yu,

Student Preparation


We are expecting students know some basis of the following items:
  • at least one AI or Deep Learning frameworks
  • Latex
  • Git
  • Python programming
  • Gnuplot


5 hours


  • Skills of AI@Edge, Deep Learning Models, Distributed Computing, Security and Privacy Strengthening, Latex, GitHub.
  • Skills of author or co-author top cs conference paper.


Weekly Meeting 1:1 meeting and group meeting.


Share This