No abstract

Internet of Things (IoT) has caused significant digital disruption to the future of the digital world. With the emergence of the 5G technology, IoT would shift rapidly from aspirational vision to realworld applications. However, one of the most pressing issues in IoT is security. Routing protocols of the IoT, such as the Routing Protocol for Low-power and lossy network protocol (RPL), are vulnerable to both insider and outsider attacks with the insider ones being more challenging because they are more difficult to detect and mitigate. Among the most concerning insider attacks to RPL in IoT applications is the Version Number Attacks (VNAs) that target the global repair mechanisms by consuming resources of IoT devices, such as power, memory, and processing power, to eventually cause the IoT ecosystem to collapse. In this paper, a lightweight VNA detection model named ML-LGBM is proposed. The work on the ML-LGBM model includes the development of a large VNA dataset, a feature extraction method, an LGBM algorithm and maximum parameter optimization. Results of extensive experiments demonstrate the advantages of the proposed ML-LGBM model based on several metrics, such as accuracy, precision, F-score, true negative rate and false-positive rate of 99.6%, 99%, 99.6%, 99.3% and 0.0093, respectively. Moreover, the proposed ML-LGBM model has slower execution time and less memory resource requirement of 140.217 seconds and 347,530 bytes, making it suitable for resource-constrained IoT devices.

No abstract

The astonishing growth of sophisticated ever-evolving cyber threats and attacks throws the entire Internet-of-Things (IoT) infrastructure into chaos. As the IoT belongs to the infrastructure of interconnected devices, it brings along significant security challenges. Cyber threat analysis is an augmentation of a network security infrastructure that primarily emphasizes on detection and prevention of sophisticated network-based threats and attacks. Moreover, it requires the security of network by investigation and classification of malicious activities. In this study, we propose a DL-enabled malware detection scheme using a hybrid technique based on the combination of a Deep Neural Network(DNN) and Long Short-Term Memory(LSTM) for the efficient identification of multi-class malware families in IoT infrastructure. The proposed scheme utilizes latest 2018 dataset named as N_BaIoT. Furthermore, our proposed scheme is evaluated using standard performance metrics such as accuracy, recall, precision, F1score, and so forth. The DL-based malware detection system achieves 99.96% detection accuracy for IoT based threats. Finally, we also compare our proposed work with other robust and state-of-the-art detection schemes.

A key issue facing operators around the globe is the most appropriate way to deal with spotting black in networks. For this purpose, the technique of passive network monitoring is very appropriate; this can be utilized to deal with incisive problems within individual network devices, problems relating to the whole LAN (Local Area Network) or core network. This technique, however, is not just relevant for troubleshooting, but it can also be castoff for crafting network statistics and analyzing network enactment. In real time network scenarios, a lot of applications and/or processes simultaneously download and upload data. Sometimes, it is very difficult to keep track of all the uploaded and downloaded data. Wireshark is a tool that is normally used to track packets for analysis between two particular hosts during two particular sessions on the same network. However, Wireshark as some limitations such as it is not a good tool for keeping track of bulky network data transferred among various endpoints. On the other side, an open source solution "ntop" offers active as well as passive packet analysis which can be handy for system administrators, networkers and IT managers. Additionally, with ntop VoIP traffic can also be monitored. In this research work, the ntop solution has been deployed to a network facility and performance analysis of ntop solution for various application processes (on application layer) such as HTTP, SSDP (based on HTTPU) against their associated protocols such as TCP/IP, UDP, and VoIP have been analyzed. Additionally, above said processes and protocols have been comprehensively analyzed relating with their client/server breakdown, duration of the connection, actual throughput, total bytes (bytes received and sent) and total bandwidth consumed. This study has been helpful to see the weakest and strongest areas of a particular network in terms of analyzing and deploying network policies. This research work will help the research community to deploy ntop solution for real-time monitoring actively and passively.