A5028883514- Anomaly Detection Techniques and Applications
- Network Security and Intrusion Detection
- Digital Media Forensic Detection
- Software System Performance and Reliability
- Data Stream Mining Techniques
- IoT and Edge/Fog Computing
- Privacy-Preserving Technologies in Data
- Advanced Malware Detection Techniques
- Age of Information Optimization
- Security and Verification in Computing
- Cloud Computing and Resource Management
University of Alberta
2020-2024
Anomaly detection has become an indispensable tool for modern society, applied in a wide range of applications, from detecting fraudulent transactions to malignant brain tumors. Over time, many anomaly techniques have been introduced. However, general, they all suffer the same problem: lack data that represents anomalous behaviour. As behaviour is usually costly (or dangerous) system, it difficult gather enough such This, turn, makes develop and evaluate techniques. Recently, generative...
As the number of machine learning applications increases, growing concerns about data privacy expose limitations traditional cloud-based methods that rely on centralized collection and processing. Federated emerges as a promising alternative, offering novel approach to training models safeguards privacy. facilitates collaborative model across various entities. In this approach, each user trains locally shares only local parameters with central server, which then generates global based these...
Control theory has proven to be a practical approach for the design and implementation of controllers, which does not inherit problems non-control theoretic controllers due its strong mathematical background. State-of-the-art auto-scaling suffer from one or more following limitations: (1) lack reliable performance model, (2) using model with low scalability, tractability, fidelity, (3) being application- architecture-specific leading extendability, (4) no guarantee on their efficiency....
The Docker Hub repository contains images of applications, which allow users to do in-place upgrades benefit from the latest released features and security patches. However, prior work showed that upgrading a image not only changes main application, but can also change many dependencies. In this paper, we present methodology study performance impact an thereby focusing on We demonstrate our through case 90 official WordPress application. Our shows should be cautious conduct test before newer...
Anomaly detection has become an indispensable tool for modern society, applied in a wide range of applications, from detecting fraudulent transactions to malignant brain tumours. Over time, many anomaly techniques have been introduced. However, general, they all suffer the same problem: lack data that represents anomalous behaviour. As behaviour is usually costly (or dangerous) system, it difficult gather enough such This, turn, makes develop and evaluate techniques. Recently, generative...