In recent times, with the advancement in technology and revolution in digital information, networks generate massive amounts of data. Due to the massive and rapid transmission of data, keeping up with security requirements is becoming more challenging. Machine learning (ML)-based intrusion detection systems (IDSs) are considered as one of the most suitable solutions for big data security. Despite the progress in ML, unrelated features can drastically influence the performance of an IDS. Feature selection plays a significant role in improving ML-based IDSs. However, the recent growth of dimensionality in data poses quite a challenge for current feature selection and extraction methods. Due to high data dimensionality, feature selection methods suffer in terms of efficiency and effectiveness. In this paper, we are introducing a new process flow for filter-based feature selection with the help of a transformation technique. Generally, normalization or transformation is implemented before classification. In our proposed model, we implemented and evaluated the effects of normalization before feature selection. To present a clear analysis on the effects of power transformation, five different transformations were implemented and evaluated. Furthermore, we implemented and compared different feature selection methods with the proposed process flow. Results show that compared with existing process flow and feature selection methods, our proposed process flow for feature selection can locate a more relevant set of features with high efficiency and accuracy.

Detecting intrusion in network traffic has remained a problematic task for years. Progress in the field of machine learning is paving the way for enhancing intrusion detection systems. Due to this progress intrusion detection has become an integral part of network security. Intrusion detection has achieved high detection accuracy with the help of supervised machine learning methods. A key factor in enhancing the performance of supervised classifiers is how data is augmented for training the classification model. Data in real-world networks or publicly available datasets are not always normally (Gaussian) distributed. Instead, the distributions of variables are more likely to be skewed. To achieve a high detection rate, data normalization or transformation plays an important role for machine learning-based intrusion detection systems. Several methods are available to normalize the attributes of the data before training a classification model. However, opting for the most suitable normalization technique is still a questionable task. In this paper, a statistical method is proposed that can identify the most suitable normalization method for the dataset. The normalization method identified by the proposed approach gives the highest accuracy for an intrusion detection system. To highlight the efficiency of the proposed method, five different datasets were used with two different feature selection methods. The datasets belong to both Internet of things and traditional network environments. The proposed method is also able to identify hybrid normalizations to achieve even improved intrusion detection results.

As cybersecurity strategies become more robust and challenging, cybercriminals are mutating cyberattacks to be more evasive. Recent studies have highlighted the use of social engineering by criminals to exploit the human factor in an organization’s security architecture. Social engineering attacks exploit specific human attributes and psychology to bypass technical security measures for malicious acts. Social engineering is becoming a pervasive approach used for compromising individuals and organizations (is relatively more convenient to compromise a human compared to discovering a vulnerability in the security system). Social engineering-based cyberattacks are extremely difficult to counter as they do not follow specific patterns or approaches for conducting an attack, making them highly effective, efficient, easy, and obscure approaches for compromising any organization. To counter such attacks, a better understanding of the attack tactics is highly essential. Hence, this paper provides an in-depth analysis of the approaches used to conduct social engineering-based cyberattacks. This study discusses human vulnerabilities employed by criminals in recent security breaches. Further, the paper highlights the existing approaches, including machine learning-based methods, to counter social engineering-based cyberattacks.

No abstract

Recent advancements in network technology and associated services have led to a rapid increase in the amount of data traffic. However, the detrimental effects caused by cyber-attacks have also significantly increased. Network attacks are evolving in various forms. Two primary approaches exist for addressing such threats: signature-based detection and anomaly detection. Although the aforementioned approaches can be effective, they also have certain drawbacks. Signature-based detection is vulnerable to variant attacks, while anomaly detection cannot be used for real-time data traffic. For resolving such issues, this paper proposes a two level classifier that can simultaneously achieve high performance and real-time classification. It employs level 1 and 2 classifiers internally. The level 1 classifier initially performs realtime detection with moderate accuracy for incoming data traffic. If the data cannot be classified with high probability by the classifier, the classification is delayed until the traffic flow terminates. The level 2 classifier then collects the statistical features of the traffic flow for performing precise classification. Compared to existing techniques, the proposed two level classification method can achieve superior performance in terms of accuracy and detection time.