A Semi-Supervised Federated Learning Scheme via Knowledge Distillation for Intrusion Detection

Yang, Linbo; Wang, Yijun; Zhi, Xue; Gui, Guan; Ohtsuki, Tomoaki

doi:10.1109/icc45855.2022.9838256

Cited by 5 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The study shows that their approach achieved significant compression while maintaining high accuracy through compressing teacher network to multi-student networks. A recent study by Zhao et al [12] proposed an Intrusion Detection (ID) method based on semi-supervised Federated Learning (FL) and knowledge distillation. The authors proposed to use knowledge distillation to solve the problems related to FL for ID, such as model parameters transmission, non-independent and identically distributed (i.i.d) data, and high communication overhead.…”

Section: B Knowledge Distillation For Iot Traffic Classificationmentioning

confidence: 99%

“…The work has been done in [24] proposes a semi-supervised FL scheme for ID, which leverages knowledge distillation to improve the performance of the student model. The proposed scheme addresses the challenges of traditional supervised and unsupervised approaches to ID by combining the benefits of semi-supervised learning, FL, and knowledge distillation.…”

Section: B Knowledge Distillation For Iot Traffic Classificationmentioning

confidence: 99%

See 1 more Smart Citation

Unleashing the Potential of Knowledge Distillation for IoT Traffic Classification

Abbasi,

Shahraki,

Prieto

et al. 2024

Trans. Mach. Learn. Comm. Netw.

View full text Add to dashboard Cite

The Internet of Things (IoT) has revolutionized our lives by generating large amounts of data, however, the data needs to be collected, processed, and analyzed in real-time. Network Traffic Classification (NTC) in IoT is a crucial step for optimizing network performance, enhancing security, and improving user experience. Different methods are introduced for NTC, but recently Machine Learning solutions have received high attention in this field, however, Traditional Machine Learning (ML) methods struggle with the complexity and heterogeneity of IoT traffic, as well as the limited resources of IoT devices. Deep learning shows promise but is computationally intensive for resource-constrained IoT devices. Knowledge distillation is a solution to help ML by compressing complex models into smaller ones suitable for IoT devices. In this paper, we examine the use of knowledge distillation for IoT traffic classification. Through experiments, we show that the student model achieves a balance between accuracy and efficiency. It exhibits similar accuracy to the larger teacher model while maintaining a smaller size. This makes it a suitable alternative for resource-constrained scenarios like mobile or IoT traffic classification. We find that the knowledge distillation technique effectively transfers knowledge from the teacher model to the student model, even with reduced training data. The results also demonstrate the robustness of the approach, as the student model performs well even with the removal of certain classes. Additionally, we highlight the trade-off between model capacity and computational cost, suggesting that increasing model size beyond a certain point may not be beneficial. The findings emphasize the value of soft labels in training student models with limited data resources.

show abstract

Section: B Knowledge Distillation For Iot Traffic Classificationmentioning

confidence: 99%

Section: B Knowledge Distillation For Iot Traffic Classificationmentioning

confidence: 99%

Unleashing the Potential of Knowledge Distillation for IoT Traffic Classification

Abbasi,

Shahraki,

Prieto

et al. 2024

Trans. Mach. Learn. Comm. Netw.

View full text Add to dashboard Cite

show abstract

“…b. DL-based Detection Methods. Till now, as one of the most popular types of ML algorithms, DL has plenty of applications in botnet detection [38,160,161,162,163,164,165,166,167,168,169,170,171,172].…”

Section: Malicious Traffic Analysismentioning

confidence: 99%

“…In addition, the weak computing power and low storage of devices in the CIoT network challenge the deployment of DL models. To solve this problem, researchers tried to combine FL with DL [160,162,163]. In 2019, Nguyen et al [160] presented a self-learning distributed system for detecting compromised devices in the CIoT network.…”

Section: Malicious Traffic Analysismentioning

confidence: 99%

“…Based on the above algorithms, researchers conducted further research to solve the problems of privacy leakage and deployment difficulty. In 2022, Zhao et al [163] pointed out that FL-based NIDS may cause privacy breaches because the transmitted model data may be used to recover private data. Meanwhile, not independent and identically distributed (non-IID) private data can affect FL in training effect, especially the distill-based FL.…”

Section: Malicious Traffic Analysismentioning

confidence: 99%

See 1 more Smart Citation

Identifying key sectors based on cascading effect along paths in the embodied CO2 emission flow network in Beijing-Tianjin-Hebei region, China

Jia

Gao

et al. 2020

Environ Sci Pollut Res

View full text Add to dashboard Cite

For the past few years, the Consumer Internet of Things (CIoT) has entered public lives. While CIoT has improved the convenience of people's daily lives, it has also brought new security and privacy concerns. In this survey, we try to figure out what researchers can learn about the security and privacy of CIoT by traffic analysis, a popular method in the security community. From the security and privacy perspective, this survey seeks out the new characteristics in CIoT traffic analysis, the state-of-the-art progress in CIoT traffic analysis, and the challenges yet to be solved. We collected 310 papers from January 2018 to December 2023 related to CIoT traffic analysis from the security and privacy perspective and summarized the process of CIoT traffic analysis in which the new characteristics of CIoT are identified. Then, we detail existing works based on five application goals: device fingerprinting, user activity inference, malicious traffic analysis, security analysis, and measurement. At last, we discuss the new challenges and future research directions.

show abstract

FedGLCD: A Federated Learning Intrusion Detection Algorithm with Combined Distillation

Liu,

Yao,

Chai

et al. 2023

2023 China Automation Congress (CAC)

View full text Add to dashboard Cite

A Semi-Supervised Federated Learning Scheme via Knowledge Distillation for Intrusion Detection

Cited by 5 publications

References 14 publications

Unleashing the Potential of Knowledge Distillation for IoT Traffic Classification

Unleashing the Potential of Knowledge Distillation for IoT Traffic Classification

Identifying key sectors based on cascading effect along paths in the embodied CO2 emission flow network in Beijing-Tianjin-Hebei region, China

FedGLCD: A Federated Learning Intrusion Detection Algorithm with Combined Distillation

Contact Info

Product

Resources

About