A

anomaly detection

Graph-based Live Anomaly Detection on Semantic Streams

Simple Arp Monitor for suspicious arp packages in the LAN

This project aim to develop a context-aware anomaly detection mechanism/model that physically observes ICPS edge devices to detect cyberattacks: https://iotgarage.net/projects/ContextAwareSecurityforIndustrialControlSystems.html

This project aim to develop a context-aware anomaly detection mechanism/model that physically observes ICPS edge devices to detect cyberattacks: https://iotgarage.net/projects/ContextAwareSecurityforIndustrialControlSystems.html

Master thesis - Deep Learning Methods Applied to Defect Detection in Industrial Images (Deep Learning-Methoden für die Defekterkennung in Industrieaufnahmen) - Tuan Anh Nguyen

This project created a dataset that captures cyber data (Network Traffic) and physical data (sensor data from primitive sensors such as temperature, humidity, motion, etc.) from a smart home with the aim of detecting complex cyber-physical anomalies. The dataset can be found here: https://dx.doi.org/10.21227/sez1-2928

This project develops video analytics towards anomaly detection on edge for smart cities under low light conditions: https://iotgarage.net/projects/VideoAnalyticstowardsAnomalyDetectionontheEdge.html

Quantum Hamiltonian-Based Models arXiv:2211.03803 [quant-ph]

In this project, we developed AnoML, which is an end-to-end data science pipeline that allows the integration of multiple wireless communication protocols, anomaly detection algorithms, and deployment to the edge, fog, and cloud platforms with minimal user interaction: https://doi.org/10.1016/j.iot.2021.100437

In this project, we developed AnoML, which is an end-to-end data science pipeline that allows the integration of multiple wireless communication protocols, anomaly detection algorithms, and deployment to the edge, fog, and cloud platforms with minimal user interaction: https://doi.org/10.1016/j.iot.2021.100437

Build a seq2seq model (with/without attention) to learn normal trajectory of ROS-based robot, then use the trained model for detection with real-time input data. This project is going along side with other ros-based node for simulating cyber-attack.

Open Source project that utilized the Public Procurement data from Paraguay, in the OCDS format, to train an Anomaly Detection Model with Isolation Forest.