suspicious-activity-detection

This is an official implement for "Detecting Suspicious Activity in the NFT Ecosystem using Temporal Graph Analysis"

PiLENS-Ai__based Suspicious Activity Detection System using Deep Learning Models and Computer Vision

Real-time fall detection & human activity recognition using YOLO26-Pose — INT8 OpenVINO/TensorRT deployment with geometry-invariant fall rules for corner-mounted CCTV.

🛡️ NodeJS, Python and PHP anti-bot protection middleware for HTTP(S) with useful proofs of work ⚡

The Log Analyzer Tool analyzes server logs to detect suspicious activities and generates reports and visualizations.

An AI-powered real-time security system that uses Computer Vision (YOLOv11) to detect weapons (guns, knives) and behavioral anomalies (loitering, falling) via live camera feeds. Features a modern React UI dashboard and a FastAPI backend.

AI Chat Monitoring & Suspicious Activity Detection System - A real-time chat application that uses Machine Learning (TF-IDF + Logistic Regression/SVM) to detect suspicious or harmful messages, trigger admin alerts, and ensure secure communication with encryption and live monitoring.

A Windows system tray application that silently monitors URLs — from your clipboard and every link you click — and warns you before a phishing page can load.

"Python-based security tool for detecting suspicious processes"

An experimental framework for evaluating AML investigation agents across grounding, safety, context engineering, compliance, and governance.

Vigil Fluminis - Windows Firewall Analysis - various criteria to generate a "suspicious" score

👁 Detect suspicious activity in real-time with AI-powered night vision surveillance on Raspberry Pi for reliable low-light security monitoring.

AML AI Investigator is a pipeline and FastAPI service for AML case evidence packages, policy retrieval (local RAG), and structured LLM copilot summaries, built on Spark‑generated case packets with Docker deployment support.

Real-Time Suspicious Activity Detection through Behavioral Modeling leverages machine learning to identify anomalies by modeling normal user/system behavior. It enables real-time threat detection, fraud prevention, and security monitoring by detecting deviations from expected patterns.

Blue Team cybersecurity project using Splunk Enterprise to investigate a simulated Fidelity-inspired security incident through detection engineering, threat hunting, dashboards, SPL queries, and MITRE ATT&CK mapping.

Data visualisation meets financial investigation

Prototype for automating Suspicious Activity Report (SAR/STR) drafting. Transforms structured transaction records into compliance-ready narratives using Python templates, with built-in evaluation for completeness, readability, and consistency.