The field of IoT security is rapidly evolving, with a focus on developing adaptive and proactive approaches to detect and prevent cyber threats. Recent research has explored the application of machine learning, deep learning, and blockchain technologies to enhance the security of IoT networks. One of the key directions in this field is the development of dynamic defense mechanisms that can intelligently identify and deploy the most effective defense against specific adversarial attacks. Another important area of research is the design of lightweight and resource-efficient intrusion detection systems that can operate effectively in resource-constrained IoT environments. Noteworthy papers in this area include DYNAMITE, which proposes a dynamic defense selection framework for enhancing ML-IDS, and ROFBSα, which introduces a real-time backup system decoupled from ML-based ransomware detection. Valkyrie is also a notable framework that can enhance any existing runtime detector with a post-detection response, limiting the impact of false positives and throttling attacks until the detector's confidence is sufficiently high.
Enhancing IoT Security through Adaptive Detection and Prevention
Sources
DYNAMITE: Dynamic Defense Selection for Enhancing Machine Learning-based Intrusion Detection Against Adversarial Attacks
ROFBS$\alpha$: Real Time Backup System Decoupled from ML Based Ransomware Detection
Application of Deep Reinforcement Learning for Intrusion Detection in Internet of Things: A Systematic Review
IoT-AMLHP: Aligned Multimodal Learning of Header-Payload Representations for Resource-Efficient Malicious IoT Traffic Classification
Impact of Latent Space Dimension on IoT Botnet Detection Performance: VAE-Encoder Versus ViT-Encoder
FLARE: Feature-based Lightweight Aggregation for Robust Evaluation of IoT Intrusion Detection
Valkyrie: A Response Framework to Augment Runtime Detection of Time-Progressive Attacks
Blockchain Meets Adaptive Honeypots: A Trust-Aware Approach to Next-Gen IoT Security
A Collaborative Intrusion Detection System Using Snort IDS Nodes
Range and Topology Mutation Based Wireless Agility
RAGAT-Mind: A Multi-Granular Modeling Approach for Rumor Detection Based on MindSpore
MindFlow: A Network Traffic Anomaly Detection Model Based on MindSpore
STGen: A Novel Lightweight IoT Testbed for Generating Sensor Traffic for the Experimentation of IoT Protocol and its Application in Hybrid Network