I am currently Ph.D student of Computer Science at North Carolina State University, where I am fortunately advised by Prof. Xiaorui Liu. Prior to that, I got my M.S. degree in Applied Mathematics at Academy of Mathematics and Systems Science, Chinease Academy of Sciences, advised by Lingyun Wu. I received my B.S. degree in Applied Mathematics at Beijing Normal University, where I was advised by Huajie Chen and Li Cui.
I have several research experiences in industry, including Amazon GuardDuty, Baidu, Inc., Tsinghua AIR, and AiQuant.
I am a big fan of basketball and I idolize Chris Paul and Allen Iverson. Our team won two champions in basketball match in BNU.
💗 Research Interests
- Adversarial Robustness on Vision, Language, and Graphs
- Graph Neural Networks
- AI for Science
🔥 News
- 🎉 2025.03: Our paper "Boosting Adversarial Robustness and Generalization with Structural Prior." is accepted by ICLR 2025 Workshop XAI4Science.
- 🎉 2025.02: Our "Robustness Reprogramming for Representation Learning" is selected as a Spotlight paper (1.4% ≈ 162/11670) by ICLR 2025.
- 📖 2025.02: New preprint: Boosting Adversarial Robustness and Generalization with Structural Prior.
- 🎉 2025.01: Our paper "Robustness Reprogramming for Representation Learning" is accepted by ICLR 2025. See you in Singapore! It explores an intriguing and fundamental open challenge in Trustworthy AI: Given any well-trained deep learning model, can it be reprogrammed to enhance its robustness?
- 📖 2024.12: New preprint: Post-hoc Interpretability Illumination for Scientific Interaction Discovery. https://arxiv.org/abs/2412.16252
- 📖 2024.11: New preprint: Exploring the Potentials and Challenges of Using Large Language Models for the Analysis of Transcriptional Regulation of Long Non-coding RNAs. https://arxiv.org/abs/2411.03522
- 🎉 2024.10: One paper is accepted by IEEE BigData 2024.
- 💻 2024.10: I give a tutorial at DSAA about "Adversarial Robustness in Graph Neural Networks".
- 📖 2024.10: New preprint: Robustness Reprogramming for Representation Learning. https://arxiv.org/abs/2410.04577
- 🎉 2024.09: Three papers are accepted by NeurIPS 2024. See you in Vancouver!
- 📖 2024.08: I will serve as a reviwer of ICLR 2025.
- 🎉 2024.07: I receive the National AI Research Resource Pilot Award for our research on exploring and enhancing the robustness of LLMs and foundation models.
- 💻 2024.05: I join Amazon AWS GuardDuty as an Applied Scientist intern at NYC.
- 🎉 Our tutorial on "Adversarial Robustness in Graph Neural Networks" is accepted by DSAA 2024. See you in San Diego!
- 🎉 2024.05: I receive the Summer Graduate Merit Awards.
- 🎉 2024.03: One paper is accepted by ICLR 2024 Workshop on Reliable and Responsible Foundation Models.
- 🎉 2024.02: One paper is accepted by Briefings in Bioinformatics.
- 🎉 2023.09: One paper is accepted by NeurIPS 2023. See you in New Orleans!
- 🎉 2023.09: One paper is accepted by BMC Bioinformatics.
- 💻 2023.06: I join Big Search team in Baidu, Inc. as a research intern at Beijing.
- 💻 2022.03: I join Institute for AI Industry Research, Tsinghua University as a research intern.
📝 Publications
As a researcher with a background in both Mathematics and AI, I am deeply engaged in developing robustness-informed neural networks using robust statistics and optimization theories. Feel free to explore my publications contributing to this topic in various domains:
- Graph: [NeurIPS 2024] Robust Graph Neural Networks via Unbiased Aggregation
- Language: [NeurIPS 2024] ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
- Vision: [ICLR 2025] Robustness Reprogramming for Representation Learning

Robustness Reprogramming for Representation Learning
Zhichao Hou, MohamadAli Torkamani, Hamid Krim, Xiaorui Liu
The International Conference on Learning Representations (ICLR), 2025
Spotlight (1.4 % ≈ 162/11670)

ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
Zhichao Hou, Weizhi Gao, Yuchen Shen, Feiyi Wang, Xiaorui Liu
Neural Information Processing Systems (NeurIPS), 2024

Robust Graph Neural Networks via Unbiased Aggregation
Zhichao Hou, Ruiqi Feng, Tyler Derr, Xiaorui Liu
Neural Information Processing Systems (NeurIPS), 2024

Boosting Adversarial Robustness and Generalization with Structural Prior
Zhichao Hou, Weizhi Gao, Hamid Krim, Xiaorui Liu
Preprint, 2025

Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
Weizhi Gao, Zhichao Hou, Han Xu, Xiaorui Liu
Neural Information Processing Systems (NeurIPS), 2024

Equivariant spatio-temporal attentive graph networks to simulate physical dynamics
Zhichao Hou*, Liming Wu*, Jirui Yuan, Yu Rong, Wenbing Huang
Neural Information Processing Systems (NeurIPS), 2023

Post-hoc Interpretability Illumination for Scientific Interaction Discovery
Ling Zhang, Zhichao Hou, Tingxiang Ji, Yuanyuan Xu, Runze Li
ICLR Workshop XAI4Science, 2025

Wei Wang, Zhichao Hou, Xiaorui Liu, Xinxia Peng
Preprint, 2024

Automated Polynomial Filter Learning for Graph Neural Networks
Wendi Yu, Zhichao Hou, Xiaorui Liu
IEEE International Conference on Big Data (IEEE BigData), 2024

HLogformer: A Hierarchical Transformer for Representing Log Data
Zhichao Hou, Mina Ghashami, Mikhail Kuznetsov, MohamadAli Torkamani
Preprint, 2024

PathExpSurv: pathway expansion for explainable survival analysis and disease gene discovery
Zhichao Hou, Jiacheng Leng, Jiating Yu, Zheng Xia, Ling-Yun Wu.
BMC Bioinformatics, 2023

Jiating Yu, Jiacheng Leng, Zhichao Hou, Duanchen Sun, Ling-Yun Wu.
Briefings in Bioinformatics, 2024

Can Directed Graph Neural Networks be Adversarially Robust?
Zhichao Hou, Xitong Zhang, Wei Wang, Charu C Aggarwal, Xiaorui Liu
Preprint, 2023
🎖 Honors and Awards
- 🏀 2018.12 Champion of Mingyue Cup Basketball Match of BNU
- 🏆 2017/2018/2019 First-class scholarship of Beijing Normal University
📖 Educations
2023.06 - (now), PhD in Computer Science, North Carolina State University, Raleigh
2020.09 - 2023.06, MS in Mathematics, Academy of Mathematics and Systems Science, Beijing
2016.09 - 2020.06, BS in Mathematics, Beijing Normal University, Beijing
💬 Invited Talks
- 2024.10, Tutorial: “Adversarial Robustness in Graph Neural Networks: Recent Advances and New Frontier”, DSAA 2024, San Diego
- 2024.03, Robustify Transformers via Plug-and-Play Paradigm, MSU
- 2024.01, Research Lightning Talk on Large Language Models and AI Security, NCSU
💻 Internships
2024.05 - 2024.08, Amazon GuardDuty, New York. Mentor: Ali Torkamani
2023.06 - 2023.09, Baidu, Inc., Beijing. Mentor: Xiaochi Wei
2022.03 - 2022.09, Institute for AI Industry Research, Tsinghua University, Beijing. Mentor: Wenbing Huang
2021.08 - 2021.10, AiQuant, Beijing. Mentor: Ge Wang
🏀 Basketball is Life