The proliferation of various connected platforms, including Internet of things, industrial control systems (ICSs), connected cars, and in-vehicle networks, has resulted in the simultaneous use of multiple protocols and devices. Chaotic situations caused by the usage of different protocols and various types of devices, such as heterogeneous networks, implemented differently by vendors renders the adoption of a flexible security solution difficult, such as recent deep learning-based intrusion detection system (IDS) studies. These studies optimized the deep learning model for their environment to improve performance, but the basic principle of the deep learning model used was not changed, so this can be called a next-generation IDS with a model that has little or no requirements. Some studies proposed IDS based on unsupervised learning technology that does not require labeled data. However, not using available assets, such as network packet data, is a waste of resources. If the security solution considers the role and importance of the devices constituting the network and the security area of the protocol standard by experts, the assets can be well used, but it will no longer be flexible. Most deep learning model-based IDS studies used recurrent neural network (RNN), which is a supervised learning model, because the characteristics of the RNN model, especially when the long-short term memory (LSTM) is incorporated, are better configured to reflect the flow of the packet data stream over time, and thus perform better than other supervised learning models such as convolutional neural network (CNN). However, if the input data induce the CNN’s kernel to sufficiently reflect the network characteristics through proper preprocessing, it could perform better than other deep learning models in the network IDS. Hence, we propose the first preprocessing method, called “direct”, for network IDS that can use the characteristics of the kernel by using the minimum protocol information, field size, and offset. In addition to direct, we propose two more preprocessing techniques called “weighted” and “compressed”. Each requires additional network information; therefore, direct conversion was compared with related studies. Including direct, the proposed preprocessing methods are based on field-to-pixel philosophy, which can reflect the advantages of CNN by extracting the convolutional features of each pixel. Direct is the most intuitive method of applying field-to-pixel conversion to reflect an image’s convolutional characteristics in the CNN. Weighted and compressed are conversion methods used to evaluate the direct method. Consequently, the IDS constructed using a CNN with the proposed direct preprocessing method demonstrated meaningful performance in the NSL-KDD dataset.

A cyber-physical infrastructure system (CPIS) is a system that controls and manages critical infrastructure such as smart manufacturing, water treatment facilities, power generation, and distribution facilities. Although these CPISs focus on the security of air-gapped network environments, strict isolation from the outside network is difficult to achieve, leading to various attacks. CPISs also comprise various devices and proprietary communication protocols that are used exclusively for each domain and site. Therefore, experts have to adopt a customized strategy to enhance security in CPIS networks after analyzing each domain, device, and protocol in advance. These methods require a significant amount of time, cost, and manpower; consequently, they are difficult to apply existing security methods in the real field. As a solution, a method is proposed herein that includes the following: 1) inferencing the CPIS protocol format and field semantics based on the characteristics of CPIS networks and protocols; 2) multilevel anomaly detection based on the meaning and values of each inferred field. The proposed method does not require knowledge of each site and protocol. In addition, the inference method can be used to analyze the payload field, including the state and measurement value, as well as the header field. Finally, we validate the proposed technique using an open-source CPIS network dataset including response injection, command injection, denial-of-service, and reconnaissance attacks. In addition, in the aspect of detection efficiency, the proposed technique exhibits comparable performance to that of existing knowledge-based anomaly detection methods.

KSII Transactions on Internet and Information Systems TIIS Paper Details

Several cases of Industrial Internet of Things (IIoT) attacks with zero-day vulnerabilities have been reported. To prevent these attacks, it is necessary to apply an abnormal behavior detection method; however, there are three main problems that make it hard. First, there are various industrial communication protocols. Instead of IT environments, many unstandardized protocols, which are usually defined by vendors, are used. Second, legacy devices are commonly used, not only EOS (End-of-service), but also EoL (End-of-Life). And last, the analysis of collected data is necessary for defining normal behavior. This behavior should be separately defined in each IIoT. Therefore, it is difficult to apply abnormal behavior detection in environments where economic and human investment is difficult. To solve these problems, we propose a deep learning based abnormal behavior detection technique that utilizes IIoT communication patterns. The proposed method uses a deep learning technique to train periodic data acquisition sequences, which is one of the common characteristics of IIoT. The trained model determined the sequence of packet is normal. The proposed technique can be applied without an additional analysis. The proposed method is expected to prevent security threats by proactively detecting cyberattacks. To verify the proposed method, a dataset was collected from the Korea Electric Power Control System. The model that defines normal behavior based on the application layer exhibits an accuracy of 79.6%. The other model, defining normal behavior based on the transport layer, has an accuracy of 80.9%. In these two models, most false positives and false negatives only occur when the abnormal packet is in a sequence.

In this paper, a data aggregation gateway framework (DA-GW) for constrained application protocol (CoAP) group communications is proposed. The DA-GW framework is designed to improve the throughput performance and energy efficiency of group communication to monitor and control multiple sensor devices collectively with a single user terminal. The DA-GW consists of four function blocks—the message analyzer, group manager, message scheduler and data handler—and three informative databases—the client database, resource database and information database. The DA-GW performs group management and group communication through each functional block and stores resources in the informative databases. The DA-GW employs international standard-based data structures and provides the interoperability of heterogeneous devices used in various applications. The DA-GW is implemented using a Java-based open source framework called jCoAP to evaluate the functions and performance of the DA-GW. The experiment results showed that the DA-GW framework revealed better performance than existing group communication methods in terms of throughput and energy consumption.