دانلود رایگان مقاله انگلیسی معماری تشخیص نفوذ ترکیبی برای اینترنت اشیا - IEEE 2016

Abstract

In computer networks, Internet of things (IoT) is an emerging paradigm wherein smart and resource-constrained objects can connect to Internet by using a wide range of technologies. Due to the insecure nature of Internet and also wireless sensor networks (WSNs), which are the main components of IoT, implementing security mechanisms in IoT seems necessary. To deal with intrusions which may occur in IoT, a novel intrusion detection architecture model for IoT is proposed in this paper. This model is based on MapReduce approach with the aim of distributed detection. To provide multifaceted detection (from the Internet and WSNs sides), the proposed model consists of anomaly-based and misuse-based intrusion detection agents that use supervised and unsupervised optimum-path forest model for intrusion detection. The experimental results of simulated scenarios show the superior performance of proposed method in intrusion detection for IoT.

V. CONCLUSION

The IoT is a worldwide network in which all heterogeneous objects around us can connect to the unreliable Internet by using a wide range of technologies. Since IoT is a hybrid network, which is composed of the Internet and the networks with heterogeneous nodes; hence, it provides accessibility to the Internet for all physical objects. Therefore, for the insecure nature of the Internet and also WSNs, which are the main components of IoT, implementing security mechanisms in IoT seems necessary. This paper proposed a novel hybrid architecture based on MapReduce for detecting both of insider and cyber attacks in IoT. The proposed model used a real-time anomaly detection module based on unsupervised OPF for detecting insider (internal) attacks which may be happened in 6LoWAPN. On the other hand, a misuse-based intrusion detection engine, which was based on supervised OPF, was responsible for detecting cyber (external) attacks that may be occurred from Internet (or LANs) side. The experimental results show the superior performance in simultaneous detection of the insider and cyber attacks in IoT.