Backdoor Attack against Log Anomaly Detection Models
Backdoor attack framework exposing vulnerabilities in log anomaly detection models.
🚀He Cheng
(he/him)
Postdoctoral Researcher in Biomedical Informatics
Professional Summary
He Cheng, Ph.D., is a Postdoctoral Researcher in the Department of Biomedical Informatics at the University of Colorado Anschutz Medical Campus, working with Dr. Yanjun Gao. His current research centers on large language model reasoning, biomedical natural language processing (BioNLP), and knowledge graphs, and he is developing LogosKG, a framework for efficient multi-hop knowledge graph retrieval.
Before that, he obtained his Ph.D. in Computer Science from Utah State University, where he conducted research on anomaly detection, explainability, and backdoor attacks in machine learning, publishing multiple first-author papers in top data mining and machine learning venues. He also holds an M.S. in Electrical and Computer Engineering from the State University of New York at Binghamton and a B.E. in Mechanical Engineering from the China University of Petroleum. Beyond research, he is passionate about applying AI to healthcare, and enjoys hiking, coding new tools, and exploring interdisciplinary applications of machine learning.
Education
Ph.D. Computer Science
Utah State University
M.S. Electrical & Computer Engineering
State University of New York at Binghamton
B.E. Mechanical Engineering
China University of Petroleum
Interests
Large Language Models (LLMs)
Natural Language Processing (NLP)
Knowledge Graphs and Reasoning
Interpretable Machine Learning
Model Robustness
📚 My Research
I am a Postdoctoral Researcher in the Department of Biomedical Informatics at the University of Colorado Anschutz Medical Campus, working with Dr. Yanjun Gao.
My current research focuses on LLM reasoning, biomedical natural language processing (BioNLP), and knowledge graphs, with an emphasis on developing methods that enhance interpretability, robustness, and scalability.
I am the lead developer of LogosKG, a framework for efficient multi-hop retrieval on large biomedical knowledge graphs, and I have also worked extensively on anomaly detection, including projects on counterfactual explanations (CFDet) and backdoor attack/defense frameworks (BLOG, BA-OCAD, BadSAD).
Beyond research, I enjoy hiking, coding new tools, and exploring interdisciplinary applications of AI in healthcare.
Featured Publications
Achieving Counterfactual Explanation for Sequence Anomaly Detection
Counterfactual explanations for sequence anomaly detection, providing interpretable insights.
Recent Publications
(2025).
Backdoor Attack against Log Anomaly Detection Models.
In Companion Proceedings of the ACM Web Conference 2025 (WWW 2025).
(2024).
Achieving Counterfactual Explanation for Sequence Anomaly Detection.
In European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML PKDD 2024).
(2024).
Backdoor Attack Against One-Class Sequential Anomaly Detection Models.
In Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD 2024).
(2023).
Explainable Sequential Anomaly Detection via Prototypes.
In International Joint Conference on Neural Networks (IJCNN 2023).
(2022).
Sequential Anomaly Detection with Local and Global Explanations.
In IEEE International Conference on Big Data (Big Data 2022).