About Me

visitors

Hello, I am Tinghao(Vitus) Xie 谢廷浩, a senior undergraduate student majoring in Computer Science and Technology at Zhejiang University. I will be a ECE PhD candidate at Princeton in Sep 2022.

I found the robustness of machine learning being both a “dark cloud” and an attractive perspective to work on. Specifically, my research interest could be described in two aspects: First, I intend to study and solve security concerns involving current non-robust deep learning models; Second, I would like to better understand AI’s behaviors and make their predictions more human-like through explainable and causal methods. In summary, I hope to fully explore the breadth and depth of secure, robust, and reliable AI. Yet, I’m always on my way looking for things that intrigue me, and tend to hold an open mind for whatever is coming. I (wish to) have fun doing research.

Earlier, I finished our project Subnet Replacement Attack (SRA)[paper][code] (CVPR’22 Oral) of the first gray-box and physically realizable backdoor weight attack, collaborating with Xiangyu Qi at Princeton University, advised by Principal Researcher Jifeng Zhu at Tencent Zhuque Lab and Prof. Kai Bu at ZJU. I was also fortunate to work with Prof. Ting Wang on backdoor certification[preview] and backdoor restoration[preview] at Pennsylvania State University as an intern, meanwhile co-advised by Prof. Shouling Ji at ZJU NESA Lab. Even before, I worked with Prof. Jianhai Chen, designed and implemented Enchecap[code], an encrypted (enclave-based) heterogeneous calculation protocol.

News & Facts