Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A curated list of Graph/Transformer-based fraud, anomaly, and outlier detection papers & resources
| Date | Stars |
|---|---|
| 2026-07-24 | 1871 |
| 2026-07-25 | 1870 |
| 2026-07-28 | 1870 |
| 2026-07-30 | 1870 |
| 2026-08-06 | 1870 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<div align="center">
<h1>Awesome Graph/Transformer Fraud Detection</h1>
<a href="https://awesome.re"><img src="https://awesome.re/badge.svg"/></a>
<a href="https://github.com/safe-graph/graph-fraud-detection-papers/stargazers"><img src="https://img.shields.io/github/stars/safe-graph/graph-fraud-detection-papers?style=flat"/></a>
<a href="http://makeapullrequest.com"><img src="https://img.shields.io/badge/PRs-welcome-brightgreen.svg?style=flat-square"/></a>
<a href="https://safe-graph.github.io/paper_dashboard/"><img src="https://img.shields.io/badge/github-website-pink?logo=github"/></a>
<a href="https://github.com/safe-graph/paper_chatbot"><img src="https://img.shields.io/badge/github-chatbot-orange?logo=github"/></a>
</div>
A curated list of Graph/Transformer-based papers and resources for fraud, anomaly, and outlier detection.
We have an [interactive dashboard](https://safe-graph.github.io/paper_dashboard/) to view/filter/search the papers listed in this repo.
To facilitate deep research, we developed a local [RAG-based LLM chatbot](https://github.com/YingtongDou/paper_chatbot) with 250 publicly accessible papers. Please refer to the project README on how to deploy this chatbot for personal use.
**Table of Contents**
- [LLM and Transformer Papers](#llm-and-transformer-papers)
- Deep Learning Graph Papers: [2026](#2026-back-to-top) | [2025](#2025-back-to-top) | [2024](#2024-back-to-top) | [2023](#2023-back-to-top) | [2022](#2022-back-to-top) | [2021](#2021-back-to-top) | [2020](#2020-back-to-top) | [Before 2020](#before-2020-back-to-top)
- [Non-Deep-Learning Graph Papers since 2014](#non-deep-learning-papers-since-2014-back-to-top)
- [Toolbox](#toolbox-back-to-top)
- [Dataset](#dataset-back-to-top)
- [Survey Paper](#survey-paper-back-to-top)
- [Other Resource](#other-resource-back-to-top)
## LLM and Transformer Papers
| Year | Title | Venue | Paper | Code |
|-------|--------|--------|--------|-----------|
| 2026 | **TransactionGPT** | KDD 2026 | [Link](https://arxiv.org/pdf/2511.08939) | Link |
| 2026 | **SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection** | arXiv 2026 | [Link](https://arxiv.org/pdf/2606.08146) | Link |
| 2026 | **Plan First, Judge Later, Run Better: A DMAIC-Inspired Agentic System for Industrial Anomaly Detection** | arXiv 2026 | [Link](https://arxiv.org/pdf/2606.04599) | Link |
| 2026 | **Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection** | arXiv 2026 | [Link](https://arxiv.org/pdf/2605.28524) | Link |
| 2026 | **UniDetect: LLM-Driven Universal Fraud Detection across Heterogeneous Blockchains** | arXiv 2026 | [Link](https://arxiv.org/pdf/2604.12329) | [Link](https://github.com/msy0513/UniDetect) |
| 2026 | **PRAGMA: Revolut Foundation Model** | arXiv 2026 | [Link](https://arxiv.org/pdf/2604.08649) | Link |
| 2026 | **Targeting Borderline Fraudsters: Multi-View Hypergraph Fraud Detection with LLM-Guided Contrastive Learning** | AAAI 2026 | [Link](https://ojs.aaai.org/index.php/AAAI/article/view/38588/42550) | Link |
| 2026 | **DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs** | AAAI 2026 | [Link](https://ojs.aaai.org/index.php/AAAI/article/view/38541/42503) | [Link](https://github.com/Xtra-Computing/DGP) |
| 2026 | **Autonomous Chain-of-Thought Distillation for Graph-Based Fraud Detection** | arXiv 2026 | [Link](https://arxiv.org/pdf/2601.22949) | Link |
| 2026 | **LLM-Assisted Logic Rule Learning: Scaling Human Expertise for Time Series Anomaly Detection** | arXiv 2026 | [Link](https://arxiv.org/pdf/2601.19255) | Link |
| 2026 | **Reinforcement Learning of Large Language Models for Interpretable Credit Card Fraud Detection** | arXiv 2026 | [Link](https://arxiv.org/pdf/2601.05578) | Link |
| 2026 | **Ahead of the Spread: Agent-Driven Virtual Propagation for Early Fake News Detection** | arXiv 2026 | [Link](https://arxiv.org/pdf/2601.02750) | [Link](https://github.com/IExcerpt of 107,097 characters
Read on GitHub
Yingtong Dou · Visa Research · United States
142
4
4
3
2
2
2
2
2
1
1
1
1
1
1
1
1
1
1
1
Would you bet a product on this? Bounded 0–100 and slow moving.
matched fp:d455d0a286b556bb, topic:llm, topic:foundation-models, topic:transformer
matched fp:d455d0a286b556bb, topic:papers, desc:curated list, readme:curated list