Yuguang Yao

Tony 

About Me

  • Currently on the Job Market.

  • PhD student advised by Prof. Sijia Liu in Computer Science and Engineering, Michigan State University.

Work Experience

  • Research Intern, Cisco Research, San Jose, Feb 2023 - Jun 2024

  • Research Intern, IBM Research, Boston, May 2022 - Aug 2022

  • Research Intern, DiDi AI Labs, Beijing, Dec 2017 - Feb 2018

Selected Publications

  • Yuguang Yao*, Zhuoshi Pan*, Gaowen Liu, Bingquan Shen, H. Vicky Zhao, Ramana Rao Kompella, Sijia Liu, “From Trojan Horses to Castle Walls: Unveiling Bilateral Backdoor Effects in Diffusion Models”, NeurIPS 2024. [link]

  • Yuguang Yao*, Jiancheng Liu*, Yifan Gong*, Xiaoming Liu, Yanzhi Wang, Xue Lin, Sijia Liu, “Can Adversarial Examples Be Parsed to Reveal Victim Model Information?”, submitted to WACV 2025. [link]

  • Yuguang Yao, Xiao Guo, Vishal Asnani, Yifan Gong, Jiancheng Liu, Xue Lin, Xiaoming Liu, Sijia Liu, "Reverse Engineering of Deceptions on Machine-and Human-Centric Attacks", Foundations and Trends in Privacy and Security 2024. [link]

  • Soumyadeep Pal, Yuguang Yao, Ren Wang, Bingquan Shen, Sijia Liu, “Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency”, ICLR 2024. [link]

  • Jinghan Jia, Jiancheng Liu, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu, "Model sparsity can simplify machine unlearning", NeurIPS 2023 (Spotlight). [link]

  • Aochuan Chen, Yuguang Yao, Pin-Yu Chen, Yihua Zhang, Sijia Liu, “Understanding and Improving Visual Prompting: A Label-Mapping Perspective”, CVPR 2023. [link]

  • Yuguang Yao*, Yihua Zhang*, Parikshit Ram, Pu Zhao, Tianlong Chen, Mingyi Hong, Yanzhi Wang, Sijia Liu, "Advancing Model Pruning via Bi-level Optimization", NeurIPS 2022. [link]

  • Yuguang Yao*, Yifan Gong*, Yize Li, Yimeng Zhang, Xiaoming Liu, Xue Lin, Sijia Liu, "Reverse Engineering of Imperceptible Adversarial Image Perturbations", ICLR 2022. [link]

  • Yimeng Zhang, Yuguang Yao, Jinghan Jia, Jinfeng Yi, Mingyi Hong, Shiyu Chang, Sijia Liu, “How to Robustify Black-Box ML Models? A Zeroth-Order Optimization Perspective”, ICLR 2022 (Spotlight). [link]

Research

  • Adversarial Machine Learning

  • Neural Network Pruning

  • Parameter Efficient Fine Tuning

  • Diffusion Models

Teaching

  • CSE 477 Web Application Development @ Spring 2021

  • CSE 480 Database Systems @ Fall 2020, Fall 2023, Spring 2024, Fall 2024

  • CSE 801 Big Data Analysis @ Spring 2023

Service

  • ICML’22, ICML’23, NeurIPS’24 AdvML Frontiers Chair

  • NeurIPS, CVPR, ICML, TPAMI Reviewer