Who am I ?
Introduction
I am a Software Development Engineer at SanDisk, focusing on Machine Learning and Data Science for Digital Twins of Packaging technologies.
Academic Background
I graduated with a First Class BSc. (Hons) in Mathematics from Universiti Sains Malaysia (USM). My studies focused on a combination of pure and applied mathematics, highlighting modules in geometric modeling, specifically involving Bézier curves and B-splines, as well as machine learning algorithms. During my time in university, I engaged with the tech and professional communities as a member of the Google Developer Group (GDG) on Campus USM and as a KPMG Student Ambassador.
Research & Publications
I was awarded a Gold Medal in the International Undergraduate Research, Innovation, Invention, and Design (I-URIID) competition 2025 hosted by UiTM. This recognized my work on reversible neural networks, which served as an extension to my final year project.
The resulting paper is titled:
“Confidently Wrong: Auditing Classifiers Using Reversible Generator MLP (RevGEN-MLP)”
The architecture was designed to be reversible, enabling the consistent generation of artificial samples with high confidence scores (softmax probabilities). This allows the generated samples to trick other classifiers trained on the same dataset using otherwise impossible values.
Acknowledgements
This research was partly supported by the Ministry of Higher Education (MOHE) under the Fundamental Research Grant Scheme (FRGS/1/2024/STG06/USM/02/11) and the School of Mathematical Sciences, Universiti Sains Malaysia, for funding the copyright fees and the I-URIID 2025 registration fees.