Data Security, Privacy & Trust Research

Data Security, Privacy & Trust (DSPT) Research

The DSPT research themes are created in examining the different aspects of data security, privacy and trust practices to address emergency events like COVID-19 outbreak, other e-Health measures and so on. Topics of interest include but are not limited to: context-aware access control, data security & access control, data sharing & privacy, machine learning, deep learning, security & AI, API Security, malware/ransomware detection and defence, IoT security, cloud/fog security (cloud-fog interplay), information modelling & ontology, responsibility attribution, secure health technologies, quantum security & quantum cryptography, space cyber security, and blockchain-based economic model.

Research THEMES

Dr Kayes has a collective interest in examining the different aspects of data security, privacy, trust, responsibility and access control. His research interests can be categorized into the following themes:

• RT1: Data safeguard, sharing, privacy and trust through security policy and access control

• RT2: Artificial Intelligence techniques against COVID-19 outbreak and other e-Health measures

• RT3: IoT (Internet of things) data indexing, integration, management and security

• RT4: Blockchain-Based Access Control and Future Financial Systems

• RT5: Cloud and Fog Security through Authorization and Authentication

The following are few more research ideas for HDR/Honours/Masters students to enhance research and innovation in security, privacy and trust areas.

• Modelling Unified CAAC (Context-Aware Access Control) Policies to Access Data from Multiple Sources, e.g., distributed cloud data centres, multiple oracle databases

• Applying Machine Learning to Automate CAAC Policy Specification and Decision Making

• Responsibility Control in Online Social Network (OSN) Platform: towards an Economic Model of Data Sharing/Access

• Blockchain-Based Access Control: a Data Sharing Service for Healthcare

• Privacy-Preserving Data Sharing Framework for Medical Research

• Analysing Privacy of IoT Streaming Data (e.g., Fitness Tracking Data) within Cyber-Physical System

• A Machine Learning-Based Trust Model for Autonomous Responses in High Consequence Environments

• The Use of Location Data and Information for Law and (Access Control) Security Policy Enforcement

• A New CAAC Policy Framework in Big Data Context through Machine Learning

• Context-Aware Firewall through Machine Learning and IDS (Intrusion Detection System) Rules, e.g., using iptables and Snort rules

• Context-Aware Access Control for Re-sharing of Data – in this project, students will explore different digital right management techniques and propose their own solution to control the re-sharing of personal data

• How to Make Machine Learning Fair and Ethical – Currently, machine learning algorithms are biased based on the datasets they are trained. In this project, students will explore different ways, so that we can immune our ML algorithms from any bias, especially from historical datasets

• Visualization of Privacy Policy and Its Implications – In this project, students will read the privacy policies of popular web service provider (e.g., Google, Facebook, Amazon) and visually show them to the user. Finally, they will present a risk assessment of their personal data based on the specific privacy policy

• Can We Enforce Privacy Policy? – One of the main problem with privacy policies is that, it is usually very difficult to enforce. In this project, student will survey the available privacy legislation related to personal data. They will also survey the existing privacy policy languages/framework. Then finally, they will propose a framework to enforce the privacy requirements outlined in the legislation