Agenda:
1 pm to 1:25 pm
Shalini Ghosh, PhD & Saurabh Nagrecha, PhD. Google Ads Safety & Integrity
1:25 pm to 3:00 pm
[1:25 pm to 1:55 pm] Prof. Nitesh Chawla, University of Notre Dame
[1:55 pm to 2:25 pm] Prof. Chanyoung Park, KAIST Detecting Change, Not Just State: Change-Aware Graph Learning for Evolving Fraud and Abuse
[2:25 pm to 2:55 pm] Prof. Jaemin Yoo, Seoul National University
[2:55 pm to 3:00 pm] Q&A Buffer
3 pm to 3:30 pm
Note to Presenters: Please set up poster boards during this break.
[3:30 pm to 3:40 pm] Coordination-Kernel Compression for Event Sequences: Learnable Pair-Interaction Models for Temporal Coordination Detection, Agus Sudjianto (GeometriX Intelligence)
[3:40 pm to 3:50 pm] Less Is More: Known Pattern Anchoring Reduces Novel Fraud Detection in LLMs, Taehun Kim, Mingzhe Wu, Guoxiang Ding (Coupang Inc.)
[3:50 pm to 4:00 pm] Toward Effective LLM Jailbreaking via Knowledge-Decomposed Adversarial Trajectory Mining and Sequential Context Synthesis, Dae-Young Park (Financial Security Institute), Kyuhong Hwang, Isaac Lee (Theori)
[4:00 pm to 4:10 pm] ProFraudGuard: Proactive Adversarial Fine-Tuning of Fraud Detectors with Inverse Reinforcement Learning, Chirag Singh, Jitin Kumar, Arunkalyan Nagarajan (Amazon India Development Center)
[4:10 pm to 4:20 pm] CloudSplat: Distributional Contrastive Learning for Tabular Data, Amir Raza, Mayank Jauhari, Anurag Tripathi, Vikash Sharma, Vipul Joshi, Christos Faloutsos (Amazon)
[4:20 pm to 4:30 pm] BASYS-INFER: A Multi-Agent Framework for Detecting Fraud, Waste, and Abuse in Medicare Claims, Srinidhi Moodalagiri, Amber Nigam, Arpan Saxena, Shen Wang, Dan Roth (Basys.ai)
4:30 pm to 4:40 pm - Closing remarks
Mitigating Disclosure Risk of Tabular Generative Model for Financial Fraud Detection with Differentially Private Multi-view Hypergraph Representation Learning, Dae-Young Park, Idealhwa Lee, Jinyoung Jung (Financial Security Institute)
TACTIC: Using Agentic LLMs to Predict Toxicity Trajectories of Online Inflammatory and Abusive Content, Anika Basu (Harker School)
SimGuard: Context-Aware Anomaly Filtering via Similarity-Guided Error Detection, Amir Raza, Mayank Jauhari, Vipul Joshi, Vikash Sharma, Rishabh Yadav, Anurag Tripathi (Amazon)