Masataka Nakahara
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Masataka Nakahara has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Ayumu Kubota
KDDI Research, Inc., 2-1-15 Ohara, Fujimino 356-8502, Saitama, Japan
3 shared publications - Norihiro Okui
KDDI Research, Inc., Saitama, Japan
3 shared publications - Gustavo Batista
University of New South Wales
2 shared publications - Hassan Habibi Gharakheili
University of New South Wales, Sydney, Australia
2 shared publications - Shayan Azizi
UNSW Sydney, Sydney, Australia
2 shared publications Ayumu Kubota
Cyber Security Laboratory, KDDI Research, Inc, Saitama, Japan
1 shared publication
Latest Publications
- Open Access
- 13 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 105-110
Towards Label Shift Adaptation for Robust IoT Device Identification
- 13 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 105-110
Open AccessTowards Label Shift Adaptation for Robust IoT Device Identification
- Open Access
- 27 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Security & Privacy
- Vol. 23 (2) , 61-70
Data Acquisition Framework for Micromobility Vehicles Toward Driving Risk Prediction Against Cyberphysical Security Attack
This article proposes a data acquisition framework for quantifying cyberphysical security attack impacts on micromobility vehicles in real space. Experiments demonstrate its capability to measure security risks across diverse micromobility systems, followed by discussion toward data augmentation and risk prediction.
- 27 August 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Security & Privacy
- Vol. 23 (2) , 61-70
Open AccessData Acquisition Framework for Micromobility Vehicles Toward Driving Risk Prediction Against Cyberphysical Security Attack
This article proposes a data acquisition framework for quantifying cyberphysical security attack impacts on micromobility vehicles in real space. Experiments demonstrate its capability to measure security risks across diverse micromobility systems, followed by discussion toward data augmentation and risk prediction.
- Open Access
- 4 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 25-27
Poster: Understanding and Managing Changes in IoT Device Behaviors for Reliable Network Traffic Inference
Data-driven inference from network traffic is increasingly becoming a practical, cost-effective, and scalable method for various use cases, among them managing the cyber health of Internet-of-Things (IoT) networks. However, inference models trained on IoT device traffic patterns from constrained environments for limited periods may not accurately predict outcomes when new contexts are introduced or variations emerge in device behaviors. In our research, we begin by quantifying the changes in network behavior patterns across various IoT device types. This will help to explain whether, when, and how changes in the learned patterns can degrade predictions. Our preliminary experiments show that the effect of these changes on the performance highly depends on the way the model establishes its decision boundaries. We aim to develop techniques that facilitate the adaptation of trained models, enabling them to effectively address the evolution of behaviors in both temporal and spatial domains. Provided by a major Internet Service Provider (ISP) we have access to a dataset comprising nearly 400M IPFIX records from about 400 IoT devices, and collected from an IoT lab testbed, as well as 25 real smart homes from Feb'19 to Dec'23.
- 4 August 2024
- Published by Association for Computing Machinery (ACM)
- p. 25-27
Open AccessPoster: Understanding and Managing Changes in IoT Device Behaviors for Reliable Network Traffic Inference
Data-driven inference from network traffic is increasingly becoming a practical, cost-effective, and scalable method for various use cases, among them managing the cyber health of Internet-of-Things (IoT) networks. However, inference models trained on IoT device traffic patterns from constrained environments for limited periods may not accurately predict outcomes when new contexts are introduced or variations emerge in device behaviors. In our research, we begin by quantifying the changes in network behavior patterns across various IoT device types. This will help to explain whether, when, and how changes in the learned patterns can degrade predictions. Our preliminary experiments show that the effect of these changes on the performance highly depends on the way the model establishes its decision boundaries. We aim to develop techniques that facilitate the adaptation of trained models, enabling them to effectively address the evolution of behaviors in both temporal and spatial domains. Provided by a major Internet Service Provider (ISP) we have access to a dataset comprising nearly 400M IPFIX records from about 400 IoT devices, and collected from an IoT lab testbed, as well as 25 real smart homes from Feb'19 to Dec'23.
- 9 November 2022
- Published by Taylor & Francis in Enterprise Information Systems
- Vol. 17 (9)
Malware detection for IoT devices using hybrid system of whitelist and machine learning based on lightweight flow data
For the security of IoT devices, the number and type of devices are generally large, so it is important to collect data efficiently and detect threats in a lightweight way. In this paper, we propose the architecture for malware detection, a method to detect malware using flow information, and a method to decrease the amount of transmission data between the servers in this architecture. We evaluate the performance of malware detection and the amount of data before and after the data reduction. And show that the performance of malware detection is maintained even though the amount of data is reduced.
- 9 November 2022
- Published by Taylor & Francis in Enterprise Information Systems
- Vol. 17 (9)
Malware detection for IoT devices using hybrid system of whitelist and machine learning based on lightweight flow data
For the security of IoT devices, the number and type of devices are generally large, so it is important to collect data efficiently and detect threats in a lightweight way. In this paper, we propose the architecture for malware detection, a method to detect malware using flow information, and a method to decrease the amount of transmission data between the servers in this architecture. We evaluate the performance of malware detection and the amount of data before and after the data reduction. And show that the performance of malware detection is maintained even though the amount of data is reduced.