Assistant Professor
Lee Kong Chian Fellow (2024-2026)
School of Computing and Information Systems
Singapore Management University
Room 5035, 80 Stamford Rd, Singapore 178902
Email: gspang[at]smu.edu.sg; pangguansong[at]gmail.com
Phone: +65-68264864
[LinkedIn] [X] [GitHub] [Google Scholar] [ORCID] [Top2%Scientists]
Guansong Pang is a tenure-track Assistant Professor of Computer Science and a Lee Kong Chian Fellow at the School of Computing and Information Systems, Singapore Management University (SMU). He is also a faculty member of Centre on Security, Mobile Applications and Cryptography. He was a Research Fellow with the Australian Institute for Machine Learning (AIML), University of Adelaide, Australia. Before joining AIML, he received his Ph.D. at University of Technology Sydney (UTS), Australia.
He leads the Machine Learning & Applications (MaLA) Lab at SMU. His research interests include machine learning, data mining, and computer vision, with a research theme focused on recognizing and generalizing to abnormal, unknown, or unseen data for building trustworthy AI systems in open environments. Research areas of particular interest include:
Anomaly detection
Open-world machine learning (e.g., out-of-distribution detection, open-set recognition, long-tailed classification, continual learning)
Specialized foundation models for specific type of data (e.g., graphs, time series, tabular) or tasks (e.g., anomaly detection, forecasting)
Security and safety in foundation models (hallucination mitigation, deepfake detection, attacks and defenses)
He also explores some pivotal real-world applications of these areas, such as network intrusion detection, fraud detection, early detection of diseases/faults, learning from biomedicine data, industrial defect detection, and hate speech detection.
His work has received multiple prestigious recognitions/awards, including the 2020 UTS Chancellor's Award List, the World's Top 2% Scientists in 2022-2025, DSAA 2023 Best Paper Award, the Most Influential KDD 2023 Paper, and the Lee Kong Chian Fellowship award 2024.
He actively contributes to the academic communities and ecosystems, serving as Area Chair of NeurIPS, ICLR, ICML, CVPR, KDD, PAKDD, IJCAI and AAAI, Associate Editor of IEEE Transactions on Neural Networks and Learning Systems, Pattern Recognition, and Neural Networks, and Editorial Board member of IEEE Intelligent Systems and International Journal of Data Science and Analytics.
Actively looking for candidates of the following positions; feel free to get in touch if you are interested (only shortlisted candidates will be contacted):
Highly motivated PhD students with strong research experience and background in computer science (scholarships).
Visiting students.
Self-motivated students for remote research intern.
📢 New positions: Research fellows, research assistants, and grant-funded visiting PhD students on the following topics:
Multimodal LLMs for visual/sequence/graph data
Large models for anomaly detection
Security and safety in foundaiton models and agents
SMU is ranked top 30 in AI and top 65 in CS according to CSRankings 2022-2026.
My team and I will be part of the following events. You're most welcome to join and contribute.
Program Co-chair of KDD Singapore Symposium 2026, January 20, 2026, Singapore
Tutorial on "Toward Foundation Models for Detecting Abnormal Activities on Graphs" at AAAI 2026, full afternoon of January 21, 2026, Singapore
Keynote at AAAI 2026 Workshop on Automated Spatial and Temporal Anomaly Detection (ASTAD), January 26, 2026, Singapore
Keynote at AAAI 2026 Workshop on Agentic AI in Financial Services, January 26, 2026, Singapore
Special Issue on "Foundation Models for Anomaly Detection, Reasoning, and Recovery" in Pattern Recognition journal. Deadline: Mar 30, 2026
Tutorial on "Robust Graph Learning on the Web: Challenges, Methods, and Applications" at Web Conference 2026, April 13-17, 2026, Dubai, United Arab Emirates
Special Session Co-chair of PAKDD 2026, June 9-12, 2026, Hong Kong, China
Organizer of CVPR 2026 Workshop on Visual Anomaly and Novelty Detection (VAND, the 4th edition), June 3-4, 2026, Denver, United States. Deadline: Feb 26, 2026
[05/2026] Five papers on anomaly detection, federated learning, and dynamic graphs are accepted to ICML 2026
[04/2026] One paper on image anomaly detection is accepted to International Journal of Computer Vision
[04/2026] One MoE Tier-2 proposal on generalist graph anomaly detection is selected for funding
[03/2026] One paper on audiovisual anomaly detection is accepted to IEEE Transactions on Multimedia
[03/2026] One paper on protein language models is accepted to Briefings in Bioinformatics.
[02/2026] Two papers on deepfake video detection and federated learning are accepted to CVPR 2026.
[02/2026] One paper on video anomaly detection is accepted to Pattern Recognition
[01/2026] One paper on insider threat detection is accepted to ICASSP 2026
[12/2025] The 4th edition of our workshop "Visual Anomaly and Novelty Detection (VAND)" is accepted to CVPR 2026. Stay tuned!
[12/2025] One survey paper on video anomaly detection is accepted to TNNLS
[12/2025] Honored to receive IEEE TNNLS Outstanding AE Award 2025
[12/2025] One tutorial on robust graph learning is accepted to WebConf 2026
[12/2025] One paper on video anomaly grounding is accepted to Neurocomputing
[11/2025] Two papers on large VLM backdoor attacks and video anomaly understanding are accepted to AAAI 2026
[10/2025] Invited to give keynote talks at AAAI 2026 workshops on Automated Spatial and Temporal Anomaly Detection (ASTAD) and Agentic AI in Financial Services
[09/2025] Our Pattern Recognition special issue on "Foundation Models for Anomaly Detection, Reasoning, and Recovery" starts to accept submission until July 30, 2026
[09/2025] Honored to be named in the list of The World's Top 2% Scientists 2025 in both career-long and single-year categories (first time named in the career-long category; rank is 26K in 2024 and lifted to 13K this year, subfield rank is 645 out of 458,615 authors).
[09/2025] Invited to give a keynote talk ACM ICAIF 2025 workshop on AI for Financial Fraud Detection & Prevention, November 15-16, 2025
[09/2025] Three papers on graph anomaly detection, LLM hallucinations, time series foundation models are accepted to NeurIPS 2025
[09/2025] One tutorial on graph anomaly detection is accepted to AAAI 2026
[09/2025] One tutorial on financial graph learning is accepted to ICAIF 2025
[08/2025] One paper on few-shot anomaly detection is accepted to CIKM 2025
[07/2025] One paper on joint class-incremental learning and OOD detection is accepted to Pattern Recognition
[07/2025] Congratulations to Jiawen and Hezhe for receiving both the 2025 SMU SCIS Dean's List and the 2025 SMU Presidential Doctoral Fellowship awards for their significant PhD research achievements
[06/2025] Two papers on VLM-enabled anomaly and out-of-distribution detection are accepted to ICCV 2025
[06/2025] One survey paper on deep graph anomaly detection is accepted to TKDE
[05/2025] Two papers on foundation models for graph anomaly detection are accepted to KDD 2025
[05/2025] Two papers on graph transformers and spatial-temporal forecasting are accepted to ICML 2025
[04/2025] Two papers on zero-shot graph anomaly detection and LLM-driven time series forecasting are accepted to IJCAI 2025
[04/2025] One tutorial proposal on foundation models in visual anomaly detection is accepted to ICCV 2025
[04/2025] One tutorial proposal on deep graph anomaly detection is accepted to IJCAI 2025
[04/2025] One paper on open-world object detection is accepted to TNNLS
[03/2025] Our proposal on aircraft defect inspection is awarded with 2024 MTC Young Individual Research Grants (YIRG)
[03/2025] Honored to give a keynote talk at WACV 2025 Workshop on Automated Spatial and Temporal Anomaly Detection (ASTAD@WACV 2025)
[02/2025] One paper on image enhancement is accepted to CVPR 2025
[02/2025] One paper on graph anomaly detection is accepted to TKDD
[02/2025] One paper on LLM-driven log anomaly detection is accepted to PAKDD 2025
[02/2025] One paper on continual learning of multimodal LLMs is accepted to TNNLS
[01/2025] One paper on open-set graph anomaly detection is accepted to ICLR 2025
