MISP
MISP (core software) - Open Source Threat Intelligence and Sharing Platform
- 6.7k
- PHP
- AGPL-3.0
- 2 d ago
MISP (core software) - Open Source Threat Intelligence and Sharing Platform
A curated list of data mining papers about fraud detection.
Face Recognition, Face Liveness Detection, Face Anti-Spoofing, Face Detection, Face Landmarks, Face Compare, Face Matching, Face Pose, Face Expression, Face Attributes, Face Templates Extraction, Face Landmarks
Open-source ad fraud detection for small businesses using machine learning. Detect click fraud and bot traffic from Google Ads, Facebook Ads, and other platforms. Completely free.
Detection of Accounting Anomalies using Deep Autoencoder Neural Networks - A lab we prepared for NVIDIA's GPU Technology Conference 2018 that will walk you through the detection of accounting anomalies using deep autoencoder neural networks. The majority of the lab content is based on Jupyter Notebook, Python and PyTorch.
A Deep Graph-based Toolbox for Fraud Detection in TensorFlow 2.X
Free iOS library for device fingerprinting. Does not require server APIs to work, fully client-side operation. MIT license, no restrictions on usage in production.
Face recognition SDK iOS with passive liveness detection (Face Detection, Face Landmarks, Face Recognition, Face Liveness, Face Pose, Face Expression, Face attributes)
Face recognition SDK & Face liveness detection SDK (Face Detection, Face Landmarks, Face Recognition, Face Liveness, Face Pose, Face Expression, Face attributes)
Face Liveness Detection SDK. Passive liveness, tested internally following ISO/IEC 30107-3 methodology, detects printed photos, video replays and 3D masks.
Liveness detection SDK Android - Passive liveness, tested internally following ISO/IEC 30107-3 methodology, detects printed photos, video replays and 3D masks.
Liveness detection SDK iOS- Passive liveness, tested internally following ISO/IEC 30107-3 methodology, detects printed photos, video replays and 3D masks.
Unified ML platform serving two production risk models behind one API, fraud detection using a Logistic Regression pipeline at 92.4 percent accuracy and 0.90 F1, and churn prediction using a five-estimator hard-voting ensemble at 85.6 percent accuracy, with SMOTE balancing, sub-0.5 second inference, and CI-enforced 90 percent test coverage.
EfficientNet+MTCNN deepfake detection achieving 87% accuracy with 12.96% EER - Multi-modal video forensics for misinformation prevention
ProofLink checks suspicious messages, links and screenshots for scams and phishing. It gives a verdict, a risk score and the evidence behind it, with optional AI review and a 3D investigation graph.
Ensemble speaker verification achieving 97% accuracy - Intelligent fusion of MFCC+DTW (92%) and Resemblyzer CNN (94%) for voice authentication
Banking-optimized signature verification with Siamese CNN - Contrastive learning for forgery detection with high recall for fraud prevention
Production-grade OTP authentication with Twilio — SMS, voice, WhatsApp, rate limiting, fraud prevention
Next.js signup form that checks every new account's email, phone and IP with Abstract API before creating it.
Runnable Python reference implementation of CVID (Capability-Validated Inbound Descriptor) Authorization-to-Reach for spam-resistant communications, with potential relevance to 3GPP and IMT-2030 future-network environments. Includes signed grants, replay protection, atomic quotas, finality enforcement, 108 tests and ten deployment variations.
Runnable reference implementation for spam-resistant map-based business discovery using query-scoped non-bearer CVIDs, Preview-to-Unlock, separate future-contact authority, atomic quota enforcement, and communication finality. Includes 125 tests, benchmarks, deployment variations, and security documentation / Telecom Fraud Prevention