Dr Yogachandran Rahulamathavan

After obtaining Ph.D. in Signal Processing from Loughborough University in 2012, Rahul joined the Information Security group at City, University London as a Research Fellow to lead signal processing in encrypted domain research theme. During his time as research fellow, he was a security and privacy work package leader for a Large-Scale Integrated Project “SpeechXrays” funded by the European Commission.

Since April 2016, he joined Loughborough University’s post graduate campus in London as a lecturer, where he was promoted to a senior lecturer in January 2020. He is the module leader for Cybersecurity and Forensics, Principles of Artificial Intelligence and Data Analytics and Information Management modules. He is one of the recipients of British Council’s UK-India research funding in 2017 and successfully lead a project between Lboro, City and IIT Kharagpur. Currently, Rahul leads a team of three Ph.D. students and serves as the principal investigator for an industry-funded project supported by Airbus Defense.

Rahul is a Programme Director for MSc Cyber Security and Data Analytics at Loughborough University London.

• B.Sc. (Hons) Engineering, University of Moratuwa, Sri Lanka, 2008, First Class
• Ph.D. Signal Processing, Loughborough University, UK, 2012
• PG Cert in Academic Practice, Loughborough University, 2018
• Lecturer, Loughborough University, 2016 to 2020

Rahul and his students work on the following fundamental areas of research within the field of Responsible AI.

• Privacy-preserving Machine Learning: This area focuses on developing techniques and algorithms that allow machine learning models to be trained and make predictions while protecting sensitive data. Rahul and his Ph.D. student are currently investigating techniques such as federated learning and homomorphic encryption (from lattice-based cryptography) to enable machine learning in encrypted domain.
• Interpretable and Explainable AI (XAI): XAI research aims to make machine learning models more transparent and interpretable, enabling users to understand how decisions are made. Rahul and his Ph.D. student are currently investigating the potential of using 2nd order sensitivity analysis to enhance the exploitability of machine learning algorithms.

List of Publications

Visit my Google Scholar Profile to check my research publications.

Research Funding

• I Khan (Cardiff Met, PI), Y. Rahulamathavan (LU, PI), C Hewage, S. Ali, Privacy-preserving Multi-user Cryptographic Algorithm for Distributed Network, 2023 - 2026 (Airbus Endeavr Wales £120K)
• Y. Rahulamathavan (PI), SAFE: Secure and Usable IoT Ecosystem for Rural Healthcare, 2017 - 2021 (British Council Contribution £220K)

Research Products

BioOnPaper: Secure Ownership Verification Solution

BioOnPaper is an ownership verification solution designed to address the challenges of secure, privacy-enhanced, and cost-effective verification at the Edge. BioOnPaper revolutionizes how we connect physical objects (tickets, keys, documents, and more) with their rightful owners in the digital realm, all without the need for complex infrastructure or internet connectivity.

Key Features:

Biometric Enrolment and Verification: BioOnPaper offers a two-step process comprising enrolment and verification. During enrolment, users' biometric features are skillfully extracted, processed, encrypted, and seamlessly imprinted onto objects. In the verification phase, our cutting-edge algorithm rigorously compares these imprinted features with users' facial biometrics, ensuring that the bearer is the genuine owner of the object.

Robust Security, Zero Internet Dependency: Unlike traditional methods prone to errors or modern approaches requiring internet connectivity, BioOnPaper stands strong with its robust security. It eliminates the need for internet connectivity during verification, providing a secure and reliable solution for ownership validation.

Biometric Morphing Attack Protection: BioOnPaper’s advanced algorithms are engineered to outsmart biometric morphing attacks and unauthorized ownership attempts. Your data remains safe and your ownership rights protected.

Data Compression for Easy Printing: BioOnPaper ingeniously compresses biometric data, enabling easy printing on various materials. No chips or specialized equipment are required, simplifying implementation.

Privacy-Preserving Encryption: Our state-of-the-art encryption techniques ensure your biometric data remains confidential. Even the edge verification device cannot decrypt your sensitive information, preserving your privacy.

• Mr Charuka Kotagaloluwegedara-Herath-Mudi (2022 to 2025) - Privacy-preserving Federated Machine Learning
• Mr Zohaib Shahid (2022 to 2025) - Exploitability and Fairness in AI
• Mr Flavio Pinto (2018 to 2024) - Distributed Technologies to transform Anti Doping Control Mechanism

• Dr (Miss) Omattage Madushi Pathmaperuma (2018 to 2022) - Machine Learning Techniques to Classify Encrypted network Traffic
• Dr (Mr) Fei Li (2012 to 2016) - Attributed Based Encryption to Fine Grain Access Control

• Conference TPC (IEEE CNS, 2023; IEEE ICC, 2020-now; IEEE Globecom; 2019 - now)
• Conference Chair (IEEE MetaCom, 2022; PST, 2023; FHE 2023; IEEE Blockchain 2023; FCN 2023)
• Guest Editor (Hindawi , 2016; IJFCS, 2017; Sage, 2018; IEEE Access, 2019; Sensors, 2021; Springer, 2023)
• Associate Editor for IEEE Access (2020 to 2023)
• Associate Editor for Sensors (2020 to now)
• Associate Editor for Springer PPNA (2021 to now)
• General Chair for the International Workshop in Internet of Things and Security, London, 2020
• Fellow of Higher Education Academy, 2018

Keynote Talk

Rahul has been invited to deliver keynote talks by the following conferences and organizations, recognizing his expertise and contributions to the field of Privacy-preserving Machine Learning:

• Privacy-Preserving Data Sharing: Tools and Applications, Warwick University, 2023
• ICCS, Wales, UK, 2022
• Sixth International Conference on Information Technology Research, Moratuwa, Sri Lanka, 2021.
• Public Key Infrastructure and It’s Applications, Bangalore, India, 2021.

Keynote Title: Hide-and-Seek: Machine Learning in Encrypted Domain

Keynote Abstract: Machine Learning models were built using a huge amount of high-quality and application-specific data. Even though the machine learning models can only be trained at places where the data is available, anyone can use the trained model for classification tasks via the Internet. While it sounds revolutionary, the trained ML models are not readily available to users in healthcare, finance, or marketing due to privacy issues. Users do not want to share their sensitive data with service providers due to a lack of trust. Simply encrypting the data only protects them during storage and transmission. Researchers and industries are developing novel techniques known as privacy-preserving techniques to process the data in an encrypted domain to tackle the privacy issue. Homomorphic encryption plays a key role in developing privacy-preserving machine learning algorithms. While homomorphic properties exist in traditional cryptographic schemes such as RSA, this talk will focus on fully homomorphic encryption from lattice-based cryptography. We will also go through the state-of-the-art works, challenges and future trend in this domain.