Hasanen Murtadha Hassan Alyasiri

Email communication is a crucial aspect of modern interactions. With the growing volume of spam emails, there is a pressing need for more effective antispam filters to detect unwanted messages. Existing spam detection techniques often fall short, prompting researchers to leverage machine learning and artificial intelligence to enhance online security. This study introduces an advanced spam detection technique using an ensemble learning approach. First, key features are extracted from both spam and non-spam emails via the term frequency-inverse document frequency (TF-IDF) method. Several classification algorithms, including cubist, naïve Bayes, support vector machine, rpart, and ctree, are applied to classify emails on the basis of the extracted features. A stacking model that uses an evolutionary algorithm is implemented to further increase the detection accuracy. The effectiveness of the proposed methodology is evaluated on widely adopted spam datasets. The results demonstrate its robustness, achieving an accuracy of 98.39% on the Enron dataset and 98% on the SpamAssassin dataset, highlighting its efficiency and significance in spam email detection.

ne of the major concerns when transitioning emails is the potential influx of unsolicited and unwanted spam emails. These unwanted emails can clog inboxes, causing recipients to overlook important messages and opportunities. To ensure security and avoid the destructive and dangerous effect of these spam emails, machine learning and deep learning methods have been conducted to design spam detection models. In this work, a combination of embedding models and multi-layer artificial neural networks as deep learning classification models is utilized in order to introduce an approach to spam detection. The proposed classifier leverages the Bidirectional Encoder Representations from Transformers (BERT) model for word embedding, applied to the Enron-Spam dataset, offering a noteworthy technique for considerable spam detection. Experimental results demonstrate that the proposed spam detection model achieved a 99% recall rate for detecting spam emails. Notably, this model is a step forward in generality and improving the efficiency of spam detection. It presents a good attempt at presenting a solution for detecting spam emails and fake text within communication environments.

Android smartphone platforms have grown rapidly and become ubiquitous due to the fact that they have opened up new possibilities in every aspect of modern life. However, as a consequence of their widespread, such systems suffer an increasing frequency of malware attacks. New malware or modifications to existing malware are increasingly being used by attackers in such operations. Security researchers deal with a continually evolving threat environment that is broad, complicated, and ever-changing. Conventional detection methods failed to adequately protect such systems and so the security industry has started to detect systems that use machine learning techniques are becoming more common. In this work, we used an evolutionary algorithm to identify malware targeting Android smartphones. In order to evaluate our system, we compared it to different state-of-the-art algorithms. Finally, we demonstrated our proposed method's ability to detect zero-day malware. Obtained results show that our method achieved 99.11% detection accuracy, and is well-suited for detecting zero-day malware.

The Internet of Things (IoT) is revolutionising nearly every aspect of modern life, playing an ever greater role in both industrial and domestic sectors. The increasing frequency of cyber-incidents is a consequence of the pervasiveness of IoT. Threats are becoming more sophisticated, with attackers using new attacks or modifying existing ones. Security teams must deal with a diverse and complex threat landscape that is constantly evolving. Traditional security solutions cannot protect such systems adequately and so researchers have begun to use Machine Learning algorithms to discover effective defence systems. In this paper, we investigate how one approach from the domain of evolutionary computation - grammatical evolution - can be used to identify cyberattacks in IoT environments. The experiments were conducted on up-to-date datasets and compared with state of-the-art algorithms. The potential application of evolutionary computation-based approaches to detect unknown attacks is also examined and discussed.

Web services are now a critical element of many of our day-to-day activities. Their applications are one of the fastest-growing industries around. The security issues related to these services are a major concern to their providers and are directly relevant to the everyday lives of system users. Cross-Site Scripting (XSS) is a standout amongst common web application security attacks. Protection against XSS injection attacks needs more work. Machine learning has considerable potential to provide protection in this critical domain. In this article, we show how genetic programming can be used to evolve detection rules for XSS attacks. We conducted our experiments on a publicly available and up-to-date dataset. The experimental results showed that the proposed method is an effective countermeasure against XSS attacks. We then investigated the computational cost of the detection rules. The best-evolved rule has a processing time of 177.87 ms and consumes memory of 8,600 bytes.

Threats against the internet and computer networks are becoming more sophisticated, with attackers using new attacks or modi- fying existing ones. Security teams have major difficulties in dealing with large numbers of continuously evolving threats. Various artificial intel- ligence algorithms have been deployed to analyse such threats. In this paper, we explore the use of Evolutionary Computation (EC) techniques to construct behavioural rules for characterising activities observed in a system. The EC framework evolves human readable solutions that pro- vide an explanation of the logic behind its evolved decisions, offering a significant advantage over existing paradigms. We examine the potential application of these algorithms to detect known and unknown attacks. The experiments were conducted on modern datasets.