۲- IoT attack model

۳- Learning-based authentication

۴- Learning-based access control

۵- Secure IoT offloading with learning

۶- Learning-based IoT malware detection

۷- Conclusions and future work

References

Introduction

The IoT facilitates integration between the physical world and computer communication networks, and applications (apps) such as infrastructure management and environmental monitoring make privacy and security techniques critical for future IoT systems [1]–[۳]. Consisting of radio-frequency identifications (RFIDs), wireless sensor networks (WSNs), and cloud computing [4], IoT systems have to protect data privacy and address security issues such as spoofing attacks, intrusions, DoS attacks, distributed DoS (DDoS) attacks, jamming, eavesdropping, and malware [5], [6]. For instance, wearable devices that collect and send the user health data to a connected smartphone have to avoid privacy information leakage. It’s generally prohibitive for IoT devices with restricted computation, memory, radio bandwidth, and battery resources to execute computational-intensive and latency-sensitive security tasks, especially under heavy data streams [7]. However, most existing security solutions generate a heavy computation and communication load for IoT devices, and outdoor IoT devices such as cheap sensors with lightweight security protections are usually more vulnerable to attacks than computer systems. As shown in Figure 1, we investigate IoT authentication, access control, secure offloading, and malware detection.