An anonymization-based privacy-preserving data collection protocol for digital health data

Abstract

Digital health data collection is vital for healthcare and medical research. But it contains sensitive information about patients, which makes it challenging. To collect health data without privacy breaches, it must be secured between the data owner and the collector. Existing data collection research studies have too stringent assumptions such as using a third-party anonymizer or a private channel amid the data owner and the collector. These studies are more susceptible to privacy attacks due to third-party involvement, which makes them less applicable for privacy-preserving healthcare data collection. This article proposes a novel privacy-preserving data collection protocol that anonymizes healthcare data without using a third-party anonymizer or a private channel for data transmission. A clustering-based k-anonymity model was adopted to efficiently prevent identity disclosure attacks, and the communication between the data owner and the collector is restricted to some elected representatives of each equivalent group of data owners. We also identified a privacy attack, known as “leader collusion”, in which the elected representatives may collaborate to violate an individual's privacy. We propose solutions for such collisions and sensitive attribute protection. A greedy heuristic method is devised to efficiently handle the data owners who join or depart the anonymization process dynamically. Furthermore, we present the potential privacy attacks on the proposed protocol and theoretical analysis. Extensive experiments are conducted in real-world datasets, and the results suggest that our solution outperforms the state-of-the-art techniques in terms of privacy protection and computational complexity.

Privacy preserving and secure robust federated learning: A survey

“…Healthcare: The digitization of patients' health records proves advantageous for both patients and healthcare providers in terms of sharing, monitoring, tracking, and analyzing healthcare information 169 . In addition to safeguarding data collection, for instance, works 170 and 171 employed k‐anonymity methods to protect data. Furthermore, FL in the medical field contributes to the integration of healthcare data from various medical institutions, fostering research in disease prediction, personalized treatment, and related areas.…”

Hybrid Deep Learning Network Intrusion Detection System Based on Convolutional Neural Network and Bidirectional Long Short-Term Memory

“…Furthermore, ransomware grew by nearly 13%, equivalent to the increase over the previous five years [1]. In the healthcare industry, implementing network security tools is imperative to protect healthcare data against unauthorized access and disclosure under the legal, ethical, and medical domains [2]. Hence, developing an effective network security tool to protect data and detect such threats is vital, as cyber-attack frequency and complexity rise yearly and are highly variable [3].…”

Distributed K-Anonymous Location Privacy Protection Algorithm Based on Interest Points and User Social Behavior

“…There are many protection methods for the two types of location privacy mentioned above, such as differential privacy [8,9], the homomorphic encryption method [10], coordinate transformation [11], anonymous steganography, etc. K-anonymity [12] belongs to anonymous steganography, which constructs an anonymous area by combining the user's real location with K-1 virtual locations. When the requesting user sends an LBS request, the user replaces his/her real location with the anonymous area and submits it to the LSP, effectively protecting his/her personal location privacy [13,14].…”