6th ICDM MLC Workshop
November 15, 2026
Shenyang, China
Shenyang, China
| Home | Registration | Program | Directions |
| Date: | Sunday, November 15, 2026 (ICDM 2026 Main Day 3) |
| Time: | 13:30–15:30 and 15:50–18:00 (coffee break 15:30–15:50) |
| Room: | Kuala Lumpur |
| ICDM Schedule ID: | W31 |
| Time zone: | All times are China Standard Time (UTC+8) |
Keynote talks are 20 minutes (15 minutes talk + 5 minutes Q&A). Paper presentations are 12 minutes (10 minutes talk + 2 minutes Q&A). Keynote abstracts and speaker biographies are on the home page.
| Time | Type | Title & Author(s) |
|---|---|---|
| Session 1 (13:30–15:30) | Session Chair: TBD | ||
| 13:30–13:35 | Opening Remarks | |
| Keynote Session I | ||
| 13:35–13:55 | Keynote 1 | Enhancing Security and Resilience through Robust Optimization Jeremiah Birrell, Texas State University |
| 13:55–14:15 | Keynote 2 | From Foundation Models to Neuro-Symbolic Architectures: Toward Safety Assurance of Learning-Enabled CPS Xi (James) Zheng, Macquarie University |
| 14:15–14:35 | Keynote 3 | SIGuard: Guarding Secure Inference with Post Data Privacy Xiaoning (Maggie) Liu, RMIT University |
| Paper Session 1: Graph Learning, Anomaly and Deepfake Detection | ||
| 14:35–14:47 | Paper S23203 | SynthWeave: Repurposing Biometric Embeddings for Efficient Multimodal DeepFake Detection Dawid Wolkiewicz, Piotr Syga, Aleksandra Kawala-Sterniuk |
| 14:47–14:59 | Paper S23202 | Efficient Mitigation of Concept Drift in GNN-Based Intrusion Detection: Innovative Proposition of Low-Resource Adapter Tuning Franciszek Lasinski, Marek Pawlicki, Rafal Kozik, Michal Choras |
| 14:59–15:11 | Paper DM1999 | A Multidirectional Bilevel Learning Framework for Class-Generalizable Anomaly Detection Padmaksha Roy, Pooja Algikar, Lamine Mili, Almuatazbellah Boker |
| 15:11–15:23 | Paper S23211 | Structure Over Features: Adversarial Robustness of GNN Architectures for Entity-Level Bitcoin AML Subgraph Classification Joachim Szewior, Kamil Szyc |
| 15:23–15:35 | Paper S23204 | The Limit Is in the Input, Not the Model: State-Dependent Command Safety in Natural-Language Interfaces to Industrial Controllers Hemen Taukoor, Zhaoxia Wang, Venky Shankararaman |
| 15:35–15:50 | Coffee Break | |
| Session 2 (15:50–18:00) | Session Chair: TBD | ||
| Keynote Session II | ||
| 15:50–16:10 | Keynote 4 | “Do Not Mention This to the User”: Detecting and Understanding Malicious Agent Skills Yi Liu, Griffith University |
| 16:10–16:30 | Keynote 5 | The Chicken or the Egg? From Data to Knowledge and Back in Malicious Component Analysis Chengwei Liu, Nankai University |
| Paper Session 2: Large Language Models and Software Security | ||
| 16:30–16:42 | Paper S23207 | MINER: Mining Internal Knowledge from Self-Evolving Reasoning Traces for Vulnerability Detection Weidong Huang, Gangyan Zeng, Xianda Fang, Zhihao Li, Wenxin Liu, Huiyuan Zhang, Liehuang Zhu |
| 16:42–16:54 | Paper S23210 | From Retrieved Evidence to Security Outcomes: A Data-Driven Analysis of Java Security API Misuse in LLM-Generated Code Tianhe Lu, Eric Spero, Sakuna Harinda Jayasundara, Robert Biddle, Giovanni Russello |
| Paper Session 3: Robust and Applied Machine Learning for Security | ||
| 16:54–17:06 | Paper S23206 | SAGE: Similarity-Based Cleaning of Poisoned Training Data from Verified Examples Chaeeun Han, Soodeh Atefi, Yevgeniy Vorobeychik, Aron Laszka |
| 17:06–17:18 | Paper DM1371 | EarlyDeFi-Bench: DeFi Rug-Pull Warning with Entity-Isolated Evaluation Youcheng Lan, Guangyan Gan, Shaobin Shi, Jie Zou, Kwanting Leung, Hongye Wu, Yuhan Cheng |
| 17:18–17:30 | Paper S23215 | Scaling PassGAN Password Guessing: A Multi-Dataset Study of Coverage, Repetition, and Password Strength Aarav Goyal, Ali Arslan, Suleyman Uludag |
| 17:30–17:42 | Paper S23213 | ROC-Based Evaluation of CyberSecurity Threat Classification Using Logistic Regression Jolanta Tańcula, Adam Czubak, Marek Barycki |
| 17:42–18:00 | Closing Remarks | |
See the Keynote Speakers section on the home page for abstracts and speaker biographies.