오토인코더 기반 IoT 디바이스 트래픽 이상징후 탐지 방법 연구 = Autoencoder-Based Anomaly Detection Method for IoT Device Traffics

국문 초록 (Abstract)

6세대(6G) 이동통신 기술은 초고속과 초대역, 그리고 초연결성을 중심으로 발전하고 있다. 통신 기술의 발전으로 사물 인터넷(IoT) 기술에서 만물 인터넷(IoE) 기술로 확장되며 초연결 사회의 형성이 급속화되고 있다. 하지만 그와 동시에 IoT 디바이스를 대상으로 하는 보안 위협이 광범위해지고 무단 액세스나 정보 유출 등 침해사고에 대한 우려가 커지며 보안 강화 솔루션의 필요성이 증가하고 있다. 이에 따라, 본 논문에서는 IoT 보안 위협에 대응하기 위해 실시간으로 수집한 네트워크 트래픽을 활용하여 오토인코더 기반의 이상징후 탐지 모델을 구현한다. 실제 IoT 환경에서 각종 공격에 대한 IoT 디바이스 트래픽 데이터를 수집하기 어려운 점을 고려하여 비지도 학습 기반의 오토인코더 신경망을 사용하며, 학습 데이터의 노이즈 적용과 잠재 공간의 차원에 따라 서로 다른 6가지 오토인코더 모델을 구현한다. 실험을 통해 모델 성능을 비교하여 비정상적인 네트워크 트래픽을 탐지하는 이상징후 탐지 모델에 대한 성능 평가를 제공한다.

다국어 초록 (Multilingual Abstract)

The sixth generation(6G) wireless communication technology is advancing toward ultra-high speed, ultra-high bandwidth, and hyper-connectivity. With the development of communication technologies, the formation of a hyper-connected society is rapidly accelerating, expanding from the IoT(Internet of Things) to the IoE(Internet of Everything). However, at the same time, security threats targeting IoT devices have become widespread, and there are concerns about security incidents such as unauthorized access and information leakage. As a result, the need for security-enhancing solutions is increasing. In this paper, we implement an autoencoder-based anomaly detection model utilizing real-time collected network traffics in respond to IoT security threats. Considering the difficulty of capturing IoT device traffic data for each attack in real IoT environments, we use an unsupervised learning-based autoencoder and implement 6 different autoencoder models based on the use of noise in the training data and the dimensions of the latent space. By comparing the model performance through experiments, we provide a performance evaluation of the anomaly detection model for detecting abnormal network traffic.

참고문헌 (Reference)

• 1 Y. Liu, "Unmanned aerial vehicle for internet of everything : Opportunities and challenges" 155 : 66-83, 2020
• 2 Y. A. Farrukh, "SeNet-I : An approach for detecting network intrusions through serialized network traffic images" 126 : 107169-, 2023
• 3 S. P. S. Appalabatla, "Performance Analogy of Autoencoders for Image Denoising" 9 : 1-4, 2023
• 4 M. Venkatasubramanian, "IoT Malware Analysis Using Federated Learning : A Comprehensive Survey" 11 : 5004-5018, 2023
• 5 I. H. Sarker, "Internet of Things(IoT)Security Intelligence : A Comprehensive Overview, Machine Learning Solutions and Research Directions" 28 : 296-312, 2023
• 6 B. Lewandowski, "Improving Network Intrusion Detection Using Autoencoder Feature Residuals" 31-39, 2022
• 7 M. Monshizadeh, "Improving Data Generalization With Variational Autoencoders for Network Traffic Anomaly Detection" 9 : 56893-56907, 2021
• 8 L. Yasenko, "Image noise reduction by denoising autoencoder" 351-355, 2020
• 9 A. Bhardwaj, "Forensic analysis and security assessment of IoT camera firmware for smart homes" 24 (24): 100409-, 2023
• 10 S. Hore, "Empirical Evaluation of Autoencoder Models for Anomaly Detection in Packet-based NIDS" 1-8, 2023
• 11 A. A. Olazabal, "Deploying Man-In-the-Middle Attack on IoT Devices Connected to Long Range Wide Area Networks (LoRaWAN)" 1-7, 2022
• 12 G. Shi, "DANTD : A Deep Abnormal Network Traffic Detection Model for Security of Industrial Internet of Things Using High-Order Features" 10 (10): 21143-21153, 2023
• 13 W. Ahmad, "Cyber Security in IoT-Based Cloud Computing : A Comprehensive Survey" 11 (11): 16-, 2022
• 14 E.C.P. Neto, "CICIoT2023: A Real-Time Dataset and Benchmark for Large-Scale Attacks in IoT Environment" 23 (23): 5941-, 2023
• 15 D. Kim, "Anomaly Detection with Feature Extraction Based on Machine Learning Using Hydraulic System IoT Sensor Data" 22 (22): 2479-, 2022
• 16 M. Douiba, "An improved anomaly detection model for IoT security using decision tree and gradient boosting" 79 (79): 3392-3411, 2023
• 17 Q. Ma, "A Novel Model for Anomaly Detection in Network Traffic Based on Support Vector Machine and Clustering" 104 : 102215-, 2021