Intrusion detection system (IDS) is one of the implemented solutions against harmful attacks. Furthermore, attackers always keep changing their tools and techniques. However, implementing an accepted IDS system is also a challenging task. In this paper, several experiments have been performed and evaluated to assess various machine learning classifiers based on KDD intrusion dataset. It succeeded to compute several performance metrics in order to evaluate the selected classifiers. The focus was on false negative and false positive performance metrics in order to enhance the detection rate of the intrusion detection system. The implemented experiments demonstrated that the decision table classifier achieved the lowest value of false negative while the random forest classifier has achieved the highest average accuracy rate.

Users and organizations find it continuously challenging to deal with distributed denial of service (DDoS) attacks. . The security engineer works to keep a service available at all times by dealing with intruder attacks. The intrusion-detection system (IDS) is one of the solutions to detecting and classifying any anomalous behavior. The IDS system should always be updated with the latest intruder attack deterrents to preserve the confidentiality, integrity and availability of the service. In this paper, a new dataset is collected because there were no common data sets that contain modern DDoS attacks in different network layers, such as (SIDDoS, HTTP Flood). This work incorporates three well-known classification techniques: Multilayer Perceptron (MLP), Naïve Bayes and Random Forest. The experimental results show that MLP achieved the highest accuracy rate (98.63%).

— Network security engineers work to keep services available all the time by handling intruder attacks. Intrusion Detection System (IDS) is one of the obtainable mechanism that used to sense and classify any abnormal actions. Therefore, the IDS must be always up to date with the latest intruder attacks signatures to preserve confidentiality, integrity and availability of the services. The speed of the IDS is very important issue as well learning the new attacks. This research work illustrates how the Knowledge Discovery and Data Mining (or Knowledge Discovery in Databases) KDD dataset is very handy for testing and evaluating different Machine Learning Techniques. It mainly focuses on the KDD preprocess part in order to prepare a decent and fair experimental data set. The techniques J48, Random Forest, Random Tree, MLP, Naïve Bayes and Bayes Network classifiers have been chosen for this study. It has been proven that the Random forest classifier has achieved the highest accuracy rate for detecting and classifying all KDD dataset attacks, which are of type (DOS, R2L, U2R, and PROBE).

With increasing technology developments, there is a massive number of websites with varying purposes. But a particular type exists within this large collection, the so-called phishing sites which aim to deceive their users. The main challenge in detecting phishing websites is discovering the techniques that have been used. Where phishers are continually improving their strategies and creating web pages that can protect themselves against many forms of detection methods. Therefore, it is very necessary to develop reliable, active and contemporary methods of phishing detection to combat the adaptive techniques used by phishers. In this paper, different phishing detection approaches are reviewed by classifying them into three main groups. Then, the proposed model is presented in two stages. In the first stage, different machine learning algorithms are applied to validate the chosen dataset and applying features selection methods on it. Thus, the best accuracy was achieved by utilizing only 20 features out of 48 features combined with Random Forest is 98.11%. While in the second stage, the same dataset is applied to various fuzzy logic algorithms. As well the experimental results from the application of Fuzzy logic algorithms were incredible. Where in applying the FURIA algorithm with only five features the accuracy rate was 99.98%. Finally, comparison and discussion of the results between applying machine learning algorithms and fuzzy logic algorithms is done. Where the performance of using fuzzy logic algorithms exceeds the use of machine learning algorithms.

The integration of a fuzzy system and automaton theory can form the concept of fuzzy automaton. This integration allows a discretely defined state-machine to act on continuous universes and handle uncertainty in applications like Intrusion Detection Systems (IDS). The typical IDS detection mechanisms are targeted to detect and prevent single-stage attacks. These types of attacks can be detected using either a common convincing threshold or by pre-defined rules. However, attack techniques have changed in recent years. Currently, the largest proportion of attacks performed, are multi-step attacks. The goal of this paper is to introduce a novel detection mechanism for multi-step attacks built upon Fuzzy Rule Interpolation (FRI) based fuzzy automaton. In that respect, the FRI method instruments the fuzzy automaton to be able to act on a not fully defined state transition rule-base, by offering interpolated conclusion even for situations which are not explicitly defined. In the suggested model, the intrusion definition state transition rule-base is defined using an open source fuzzy declarative language. On the multi-step attack benchmark dataset introduced in this paper, the proposed detection mechanism was able to achieve 97.836% detection rate. Furthermore, in the studied examples, the suggested method was able not only to detect but also early detect the multi-step attack in stages, where the planned attack is not fully elaborated and hence less harmful. According to these results, the IDS built upon the FRI based fuzzy automaton could be a useful device for detecting multi-step attacks, even in cases when the intrusion state transition rule-based is incomplete. The early detection of multi-step attacks also allows the administrator to take the necessary actions in time, to mitigate the potential threats.

Zero-day attacks remain among the most formidable threats to modern cybersecurity, exploiting undisclosed vulnerabilities that bypass conventional detection mechanisms. In this paper, we propose a self-learning intrusion detection system (IDS) based on Deep Q-Networks (DQNs), a reinforcement learning approach capable of autonomously classifying network traffic without dependence on predefined signatures or labeled training data. Leveraging the UGRansome dataset, the model is evaluated under two experimental scenarios: a conventional random split and a more rigorous zero-day split, where ransomware families in the test set are entirely excluded from training. In binary classification, the proposed system achieves 97.6% accuracy (F1-score: 0.98) in the random split and 95.9% accuracy (F1-score: 0.96) in the zero-day setup, consistently prioritizing high recall for ransomware detection. In multiclass classification, it attains 97.0% and 92.0% accuracy in the random and zero-day splits, respectively. These results underscore the potential of reinforcement learning as a robust and adaptive foundation for real-time intrusion detection in evolving threat landscapes.