Security in IoT networks is currently mandatory, due to the high amount of data that has to be handled. These systems are vulnerable to several cybersecurity attacks, which are increasing in number and sophistication. Due to this reason, new intrusion detection techniques have to be developed, being as accurate as possible for these scenarios. Intrusion detection systems based on machine learning algorithms have already shown a high performance in terms of accuracy. This research proposes the study and evaluation of several preprocessing techniques based on traffic categorization for a machine learning neural network algorithm. This research uses for its evaluation two benchmark datasets, namely UGR16 and the UNSW-NB15, and one of the most used datasets, KDD99. The preprocessing techniques were evaluated in accordance with scalar and normalization functions. All of these preprocessing models were applied through different sets of characteristics based on a categorization composed by four groups of features: basic connection features, content characteristics, statistical characteristics and finally, a group which is composed by traffic-based features and connection direction-based traffic characteristics. The objective of this research is to evaluate this categorization by using various data preprocessing techniques to obtain the most accurate model. Our proposal shows that, by applying the categorization of network traffic and several preprocessing techniques, the accuracy can be enhanced by up to 45%. The preprocessing of a specific group of characteristics allows for greater accuracy, allowing the machine learning algorithm to correctly classify these parameters related to possible attacks.

Artificial intelligence algorithms have a leading role in the field of cybersecurity and attack detection, being able to present better results in some scenarios than classic intrusion detection systems such as Snort or Suricata. In this sense, this research focuses on the evaluation of characteristics for different well-established Machine Leaning algorithms commonly applied to IDS scenarios. To do this, a categorization for cybersecurity data sets that groups its records into several groups is first considered. Making use of this division, this work seeks to determine which neural network model (multilayer or recurrent), activation function, and learning algorithm yield higher accuracy values, depending on the group of data. Finally, the results are used to determine which group of data from a cybersecurity data set are more relevant and representative for the intrusion detection, and the most suitable configuration of Machine Learning algorithm to decrease the computational load of the system.

New computational and technological paradigms that currently guide developments in the information society, i.e., Internet of things, pervasive technology, or Ubicomp, favor the appearance of new intrusion vectors that can directly affect people’s daily lives. This, together with advances in techniques and methods used for developing new cyber-attacks, exponentially increases the number of cyber threats which affect the information society. Because of this, the development and improvement of technology that assists cybersecurity experts to prevent and detect attacks arose as a fundamental pillar in the field of cybersecurity. Specifically, intrusion detection systems are now a fundamental tool in the provision of services through the internet. However, these systems have certain limitations, i.e., false positives, real-time analytics, etc., which require their operation to be supervised. Therefore, it is necessary to offer architectures and systems that favor an efficient analysis of the data handled by these tools. In this sense, this paper presents a new model of data preprocessing based on a novel distributed computing architecture focused on large-scale datasets such as UGR’16. In addition, the paper analyzes the use of machine learning techniques in order to improve the response and efficiency of the proposed preprocessing model. Thus, the solution developed achieves good results in terms of computer performance. Finally, the proposal shows the adequateness of decision tree algorithms for training a machine learning model by using a large dataset when compared with a multilayer perceptron neural network.

Cyberattacks are part of the continuous race, where research in computer science both contributes to discovering new threats and vulnerabilities and also mitigates them. When new vulnerabilities are not reported but sold to attackers, they are called “zero-days,” and are particularly difficult to identify. Modern intrusion detection systems (IDS) that leverage artificial intelligence (AI) and machine learning (ML) are becoming essential in identifying these cyber threats. This study presents the design of an IDS using ML and Explainable AI (XAI) techniques for real-time classification of various detected cyberattacks. By utilizing frameworks such as Apache Kafka and Spark, along with libraries such as Scikit-learn and SHAP, the system identifies and classifies normal or anomalous network traffic in real-time. The XAI offers the IDS the option to explain the rationale behind each classification. The primary aim of this research is to develop a flexible and scalable IDS that can provide clear explanations for its decisions. The second aim is to compare and analyze different ML models to achieve the best results in terms of accuracy, f1, recall, and precision. Random Forest models proposed in this research article obtained the best results in figuring out the key features identified by the XAI model, which includes Ct_state_ttl, Sttl, Dmean, and Dbytes from the UNSW-NB15 dataset. Finally, this research work introduces different machine learning algorithms with superior performance metrics compared to other real-time classification methods.

Currently, the use of machine learning models for developing intrusion detection systems is a technology trend which improvement has been proven. These intelligent systems are trained with labeled datasets, including different types of attacks and the normal behavior of the network. Most of the studies use a unique machine learning model, identifying anomalies related to possible attacks. In other cases, machine learning algorithms are used to identify certain type of attacks. However, recent studies show that certain models are more accurate identifying certain classes of attacks than others. Thus, this study tries to identify which model fits better with each kind of attack in order to define a set of reasoner modules. In addition, this research work proposes to organize these modules to feed a selection system, that is, a dynamic classifier. Finally, the study shows that when using the proposed dynamic classifier model, the detection range increases, improving the detection by each individual model in terms of accuracy.

Companies, institutions or governments process large amounts of data for the development of their activities. This knowledge usually comes from devices that collect data from various sources. Processing them in real time is essential to ensure the flow of information about the current state of infrastructure, as this knowledge is the basis for management and decision making in the event of an attack or anomalous situations. Therefore, this article exposes three unsupervised machine learning models based on clustering techniques and threshold definitions to detect anomalies from heterogeneous streaming cybersecurity data sources. After evaluation, this paper presents a case of heterogeneous cybersecurity devices, comparing WSSSE, Silhouette and training time metrics for all models, where K-Means was defined as the optimal algorithm for anomaly detection in streaming data processing. The anomaly detection’s accuracy achieved is also significantly high. A comparison with other research studies is also performed, against which the proposed method proved its strong points.