Jamil Arbas

Jamil Arbas is a PhD candidate in the Department of Computer Science at Toronto Metropolitan University. He began his PhD journey after completing his Master's degree at McMaster University, where he focused on data privacy and machine learning. Broadly speaking, Jamil’s research centers around enhancing the fairness, security, and privacy of machine learning models. In recent years, he has concentrated on exploring Local Differential Privacy, optimizing privacy-utility trade-offs, and developing private learning algorithms. Jamil co-authored a paper on "Polynomial Time and Private Learning of Unbounded Gaussian Mixture Models," which was accepted by the International Conference on Machine Learning (ICML) and presented in Hawaii in July 2023.