Y. Liang

{firstname}.{lastname}@connect.ust.hk

I am currently a PhD student at HKUST, advised by Prof. Ke Yi.

I received my BMath from the University of Waterloo, my MSc Financial Mathematics and MSc Computer Science from McMaster University.

Peer-reviewed Publications:
Conference:
Liang Y, Yi K. Smooth Sensitivity for Geo-Privacy. CCS '24 [pdf | code]
Liang Y, Yi K. Concentrated Geo-Privacy. CCS '23 [pdf | code]
Dong W, Liang Y, Yi K. Differentially Private Covariance Revisited. NeurIPS '22 [pdf | code]
Huang Z, Liang Y, Yi K. Instance-optimal mean estimation under differential privacy. NeurIPS '21
Workshop:
Liang Y, Samavi R. Towards Robust Deep Learning with Ensemble Networks and Noisy Layers. (2021) AAAI RSEML Workshop [master's work]
Journal:
Liang Y, Samavi R. Optimization-based Anonymity Algorithms. Computers & Security (2020) [master's work]

Academic Service:
Reviewer for ICML 2023, NeurIPS 2023, ICML 2024, AAAI 2025

Professional Experience:
Prior to starting my PhD studies, I worked in the finance industry for 5+ years in the quantitative research and development area, specializing in large-scale monte carlo simulation engines.