Zhiyuan Cheng's Homepage

Short Bio

I am currently a Ph.D. candidate in the Department of Computer Science at Purdue University, and I am fortunate to be advised by Samuel Conte Professor Xiangyu Zhang. Previously, I obtained my bachelor’s degree with distinction in Computer Science from Wuhan University (WHU), and I am grateful to have Prof. Xiaoguang Niu (WHU) and Prof. Jiannong Cao (PolyU) as my initial advisors during my undergraduate studies.

My research interest lies at the intersection of Artificial Intelligence and Security, and I specialize in Trustworthy Machine Learning. Specifically, I focus on enhancing the robustness and security of AI-driven applications such as 3D perception, autonomous driving, robotic systems, etc. Additionally, I explore security topics around AI-generated content (AIGC) and foundation models/LLM.

Publications [ Google Scholar ]

ICLR'24

Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection

Zhiyuan Cheng, Hongjun Choi, Shiwei Feng, James Chenhao Liang, Guanhong Tao, Dongfang Liu, Michael Zuzak, Xiangyu Zhang

International Conference on Learning Representations (ICLR), 2024.

PDF BibTex

VLDB'24

GPTuner: A Manual-Reading Database Tuning System via GPT-Guided Bayesian Optimization

Jiale Lao, Yibo Wang, Yufei Li, Jianping Wang, Yunjia Zhang, Zhiyuan Cheng, Wanghu Chen, Mingjie Tang, Jianguo Wang

International Conference on Very Large Data Bases (VLDB), 2024.

PDF BibTex

SIGMOD'24

A Demonstration of GPTuner: A GPT-Based Manual-Reading Database Tuning System

Jiale Lao, Yibo Wang, Yufei Li, Jianping Wang, Yunjia Zhang, Zhiyuan Cheng, Wanghu Chen, Mingjie Tang, Jianguo Wang

International Conference on Management of Data (SIGMOD), 2024.

PDF BibTex

ICLR'23

Adversarial Training of Self-supervised Monocular Depth Estimation Against Physical-World Attacks

Zhiyuan Cheng, James Liang, Guanhong Tao, Dongfang Liu, Xiangyu Zhang

International Conference on Learning Representations (ICLR), 2023.

PDF BibTex Spotlight

ECCV'22

Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patches

Zhiyuan Cheng, James Liang, Hongjun Choi, Guanhong Tao, Zhiwen Cao, Dongfang Liu, Xiangyu Zhang

European Conference on Computer Vision (ECCV), 2022.

PDF BibTex

NDSS'22

RvPlayer: Robotic Vehicle Forensics by Replay with What-If Reasoning

Hongjun Choi, Zhiyuan Cheng, Xiangyu Zhang

Network and Distributed System Security Symposium (NDSS), 2022.

PDF BibTex

Teaching

Teaching Assistant, CS381 Introduction to the Analysis of Algorithms, 2020 Fall

Talks

Towards Secure and Robust Perception of Autonomous Vehicles in the Physical World

College of Computer Science, Chongqing University, Jan. 2024

Adversarial Training of Self-supervised Monocular Depth Estimation

Workshop on Scene Representations For Autonomous Driving, ICLR, May 2023
Youth PhD Talk-ICLR 2023, AI TIME, May 2023

Experience

Security Research Intern, Ant Group, 2022.6 ~ 2022.8
Research Intern, The Internet and Mobile Computing Laboratory (IMCL),The Hong Kong Polytechnic University (PolyU), 2018.7 ~ 2018.9

Honors & Awards

Ross Fellowship, Purdue University, 2019
Outstanding Undergraduate Thesis, Wuhan University, 2019
The Samsung Scholarship, Samsung Group, 2017
National Scholarship, China, 2016

Services

Program Committee/Reviewer

AAAI Conference on Artificial Intelligence (AAAI), 2023-2024
International Joint Conference on Artificial Intelligence (IJCAI), 2023

Sub-Reviewer

International Conference on Automated Software Engineering (ASE), 2023
AAAI Conference on Artificial Intelligence (AAAI), 2022

Conference Volunteer

International Conference on Learning Representations (ICLR), 2023

Last Update: