The digital health world has become so advanced that many tiny wearable devices can track your heart rate, and blood pressure, and even detect early signs of illness. The Internet of Things (IoT) in healthcare is revolutionizing how we monitor and manage our health daily. Unfortunately, this innovation hides beneath it many concerning and dangerous cybersecurity challenges, putting patients’ data privacy at risk that could cost more than just leaking the medical records.
This teaching aide shines light on the foundational concepts of the data privacy techniques putting a special lens on how these techniques can help in preserving patient data privacy when used in IoT healthcare devices. This presentation helps the audience to practically link these techniques with the real-life implementations of IoT. The audience will learn about cutting-edge IoT data differential privacy techniques and how each technique addresses specific IoT data privacy implementation such as LOPUP, LocoP, LaPlace, and LSTM algorithms protecting the patients’ sensitive data.
Project Team:
- Firas Shama
- Li-Qun Lu
- Tamer Zeineldin
Teaching Aide:
Walkthrough
Questions To The Audience:
- Question (1): What are the most significant privacy risks in IoT healthcare devices, and how do they affect patient data security?
- Question (2): How do IoT healthcare devices handle data collection, transmission, and storage, and where are the vulnerabilities?
- Question (3): How can advanced privacy techniques (e.g., FHIR, HL7, differential privacy, LSTM) improve healthcare data privacy and the security of IoT-based patient systems?
