Advancing Deep Learning for Graph Anomaly Detection: From Transductive Learning to Universal Generalist Models
Graph-structured data are pervasive in modern applications, including financial transaction networks, e-commerce user–item graphs, communication networks, cybersecurity logs, and social platforms. Graph anomaly detection (GAD) aims to identify irregular nodes that deviate from normal structural or feature patterns, which are widely used in fraud detection in finance, review spam detection, and abusive user detection. Despite significant advances in deep learning–based GAD, current methods predominantly face several challenges (1) Overlooking the anomaly–discriminative property "one-class homophily" and the lack of a reliable anomaly scoring approach. (2) Ignoring the fact that normal samples overwhelmingly dominate the data, making the labels for normal samples is much easier to obtain. (3) Limited generalization ability across different graphs, which restricts their effectiveness in real-world cross-graph applications. To address these challenges, this dissertation proposed (1) a novel unsupervised anomal…
Subtitle: PhD Dissertation Proposal by QIAO Hezhe. Contact: scisseminars@smu.edu.sg. Speaker Details:
QIAO Hezhe
PhD Candidate
School of Computing and Information Systems
Singapore Management University, QIAO Hezhe is a fourth-year Ph.D. candidate in Computer Science at the School of Computing and Information Systems, under the supervision of Prof. Pang Guansong. Prior to that, he received his MS degree from the University of Chinese Academy Science, China. His research interests include multi-agent system safety, graph anomaly detection, LLM hallucination detection and mitigation, and graph… RSVP: . Reserve a seat: https://forms.office.com/pages/responsepage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTbOXO7ktpRtBsn62WuekYtpURE05M0RENTVHM1cwMTVVRDJBNEhJRFE4SS4u&route=shorturl. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Friday, December 12, 2025, 9:00 AM – 10:00 AM.
Meeting room 5.1, Level 5. SMU SCIS 1, Singapore 178902.
For more info visit computing.smu.edu.sg. Evaluating and Enhancing Safety Alignment of Large Language Model
Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) demonstrate remarkable capabilities across diverse applications, yet they remain vulnerable to adversarial attacks through carefully crafted prompts and harmful visual inputs that circumvent safety mechanisms. Despite considerable efforts in reinforcement learning from human feedback (RLHF) and supervised fine-tuning, existing safeguards prove inadequate because these models operate as black-boxes without explanations for their decisions, making security vulnerabilities difficult to identify and eliminate. Addressing these challenges fundamentally requires understanding the inner safety mechanisms of these models to develop targeted mitigation strategies that can effectively defend against attacks.
This dissertation presents four interconnected contributions to improve LLM and MLLM security through mechanistic understanding. We propose CASPER, a causality analysis framework operating at token, layer, and neuron levels that reveals how…
Subtitle: PhD Dissertation Defense by ZHAO Wei. Contact: scisseminars@smu.edu.sg. Speaker Details: , ZHAO Wei
PhD Candidate
School of Computing and Information Systems
Singapore Management University, Wei ZHAO is a Ph.D. Candidate in Computer Science at Singapore Management University, under the supervision of Professor Jun SUN. His research focuses on improving large model safety through understanding and enhancing the inner mechanisms of Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs). His PhD research addresses critical security vulnerabilities in these models, spanning… RSVP: . Reserve a seat: https://forms.office.com/Pages/ResponsePage.aspx?id=ynmKyZpakUeiQ_Bq_WdGTejbEKPlArBJhZomj91naG9UMDgyWVA3R1YwVE8yRlU3SExISDRZRzNCNS4u. Type: Seminars & Workshops. Subject: Information Technology & Systems. Audience: Public. Current Student. Academic Community.
Tuesday, January 6, 2026, 9:30 AM – 10:30 AM.
Meeting room 5.1, Level 5. SMU SCIS 1, Singapore 178902.
For more info visit computing.smu.edu.sg.