UGFraud
fraud detector
A toolbox for unsupervised graph-based fraud detection using multiple algorithms and techniques
An Unsupervised Graph-based Toolbox for Fraud Detection
131 stars
4 watching
26 forks
Language: Python
last commit: over 4 years agoLinked from 1 awesome list
anomaly-detectiondata-sciencefraud-detectionfraud-preventiongraph-algorithmsmachine-learningopensourceoutlier-detectionsecurity-toolsspam-detectiontoolbox
Related projects:
| Repository | Description | Stars |
|---|---|---|
| A toolbox for building and comparing graph neural network-based fraud detection models | 698 | |
| Develops and evaluates machine learning models for detecting financial fraud | 195 | |
| Detects anomalies in graph data using various algorithms | 1,350 | |
| Develops a survival analysis-based model to detect fraud early | 34 | |
| An implementation of a graph neural network-based fraud detector designed to counter camouflaged fraudsters | 250 | |
| A Python framework for accelerating large-scale unsupervised outlier detection in heterogeneous datasets | 382 | |
| An open-source library for training and evaluating graph anomaly detection models | 64 | |
| Reproduce experiments and results from a research paper on fraud detection using machine learning algorithms. | 4 | |
| A system for detecting collective behavior of online frauds in customer reviews and ranking fraudulent reviewer groups | 19 | |
| A framework for detecting fraud using a novel neural network approach that learns from benign user data | 24 | |
| A collection of Yara rules for detecting malware evasion techniques and malicious activity. | 25 | |
| Develops a machine learning model to classify and rank customs fraud cases based on transaction-level data and tree-based features | 61 | |
| Detects hidden data in images using various steganography techniques | 1,333 | |
| A Python library for detecting outliers, adversarial examples, and data drift in various types of data | 2,262 | |
| Automatically detects obfuscated code and other complex code constructs in binaries to aid reverse engineering. | 580 |