Advancements in IoT Security and Anomaly Detection

The field of IoT security and anomaly detection is rapidly evolving, with a focus on developing robust and scalable techniques to identify and mitigate potential threats. Recent research has explored the application of deep learning models, such as ResNet-18 and GraphSAGE, to detect anomalies in IoT network traffic. Additionally, contrastive learning frameworks, like the Kolmogorov-Arnold Network (KAN), have shown promise in semi-supervised intrusion detection. The use of Mel-frequency cepstral coefficients (MFCCs) has also been investigated for adaptive spectral feature representation in IoT network traffic analysis. Furthermore, researchers have proposed various mitigation strategies against DDoS attacks, including layered mitigation strategies and machine learning-based intrusion detection systems. Noteworthy papers in this area include:

  • A paper proposing a novel approach using MFCCs and ResNet-18 for anomaly detection, demonstrating improved class separability and multiclass classification.
  • Another paper introducing a comprehensive framework for evaluating the robustness of GNN-based NIDS in IoT environments, highlighting the importance of realistic threat modeling and rigorous measurement practices. These advancements highlight the ongoing efforts to enhance the security and resilience of IoT systems, and underscore the need for continued innovation in this critical research area.

Sources

Spectral Feature Extraction for Robust Network Intrusion Detection Using MFCCs

IoT Malware Network Traffic Detection using Deep Learning and GraphSAGE Models

Contrastive-KAN: A Semi-Supervised Intrusion Detection Framework for Cybersecurity with scarce Labeled Data

Reporte de vulnerabilidades en IIoT. Proyecto DEFENDER

REAL-IoT: Characterizing GNN Intrusion Detection Robustness under Practical Adversarial Attack

How To Mitigate And Defend Against DDoS Attacks In IoT Devices

Early Detection of Furniture-Infesting Wood-Boring Beetles Using CNN-LSTM Networks and MFCC-Based Acoustic Features

Enterprise Security Incident Analysis and Countermeasures Based on the T-Mobile Data Breach

A Crowdsensing Intrusion Detection Dataset For Decentralized Federated Learning Models

Built with on top of