Project Info

Private Memoirs of IoT Devices: Safeguarding User Privacy in the IoT Era

Dong Chen
dongchen@mines.edu

Project Goals and Description:

The pervasiveness of IoT embedded devices, coupled with the introduction of machine learning frameworks (TensorFlow Lite) for Microcontrollers, will enable the mass proliferation of AI-powered IoT devices. This project will build a low-cost and open-source user privacy defense system that enables users to leverage TinyML approaches to significantly reduce the private information leaked through IoT device network traffic data, while still permitting sophisticated data analytics that is necessary in IoT environment. Students will have opportunity to deploy and benchmark TinyML systems on Arduino Tiny Machine Learning Kit and publish paper at ACM/IEEE IoTDI/IPSN. 

More Information:

Grand Challenge: Secure cyberspace.
  • Keyang Yu, Qi Li, Dong Chen, Mohammad Rahman, and Shiqiang Wang. 2021. PrivacyGuard: Enhancing Smart Home User Privacy. In Proceedings of the 20th International Conference on Information Processing in Sensor Networks (co-located with CPS-IoT Week 2021) (IPSN '21). Association for Computing Machinery, New York, NY, USA, 62–76. DOI:https://doi.org/10.1145/3412382.3458257
  • https://github.com/cyber-physical-systems/PrivacyGuard

Primary Contacts:

Dong Chen, dongchen@mines.edu

Student Preparation

Qualifications

  • Student should be familiar with basic Linux and C or Python programming and willing to learn how to program Machine learning models.
  • Familiarity with Scikit-Learn/TensorFlow is a bonus.

TIME COMMITMENT (HRS/WK)

5

SKILLS/TECHNIQUES GAINED

  • Student will develop an understanding of Machine Learning and Cybersecurity, and will also gain experience of sensor systems developing/programming to match real stakeholder needs.
  • A small publication (workshop or conference paper) is possible upon completion of the project.

MENTORING PLAN

The student will be working closely with grad students on the same project; attending weekly project meetings with faculty to discuss problems and solutions.

PREFERRED STUDENT STATUS

Freshman
Sophomore
Junior
Senior
Share This