Despite the growing popularity of machine learning models in the cyber-security applications ), most of these models are perceived as a black-box. The eXplainable Artificial Intelligence has become increasingly important to interpret the machine learning models to enhance trust management by allowing human experts to understand the underlying data evidence and causal reasoning. According to IDS, the critical role of trust management is to understand the impact of the malicious data to detect any intrusion in the system. The previous studies (...) focused more on the accuracy of the various classification algorithms for trust in IDS. They do not often provide insights into their behavior and reasoning provided by the sophisticated algorithm. Therefore, in this paper, we have addressed XAI concept to enhance trust management by exploring the decision tree model in the area of IDS. We use simple decision tree algorithms that can be easily read and even resemble a human approach to decision-making by splitting the choice into many small subchoices for IDS. We experimented with this approach by extracting rules in a widely used KDD benchmark dataset. We also compared the accuracy of the decision tree approach with the other state-of-the-art algorithms. (shrink)

To design and develop AI-based cybersecurity systems ), users can justifiably trust, one needs to evaluate the impact of trust using machine learning and deep learning technologies. To guide the design and implementation of trusted AI-based systems in IDS, this paper provides a comparison among machine learning and deep learning models to investigate the trust impact based on the accuracy of the trusted AI-based systems regarding the malicious data in IDs. The four machine learning techniques are decision tree, K nearest (...) neighbour, random forest, and naïve Bayes. The four deep learning techniques are LSTM and GRU. Two datasets are used to classify the IDS attack type, including wireless sensor network detection system and KDD Cup network intrusion dataset. A detailed comparison of the eight techniques’ performance using all features and selected features is made by measuring the accuracy, precision, recall, and F1-score. Considering the findings related to the data, methodology, and expert accountability, interpretability for AI-based solutions also becomes demanded to enhance trust in the IDS. (shrink)

In this paper, an extension of first order logic is introduced. In such logics atomic formulas may have infinite lengths. An Omitting Types Theorem is proved.

We generalize two classical results on cylindric algebra to certain expansions of cylindric algebras where the extra operations are defined via first order formulas. The first result is the Neat Embedding Theorem of Henkin and the second is Monk's classical non-finitizability result of the class of representable algebras. As a corollary we obtain known classical results of Johnson and Biro published in the Journal of Symbolic logic.

This article examines Mughulṭāy b. Qilīj’s (d. 762/1361) al-Zahr al-bāsim fī siyar Abī al-Qāsim, a ḥāshiya (gloss, marginal notes) on ʿAbd al-Raḥmān al-Suhaylī’s (d. 581/1185) commentary on Ibn Isḥāq’s Sīra. Drawing on evidence from Mamlūk-era chronicles, biographical dictionaries, and commentarial introductions, it analyzes Mughulṭāy b. Qilīj as a historical figure and the context and content of his work. This is done in order to demonstrate how commentaries and glosses are deeply related to the schol­arly and cultural life of the period. (...) These resources testify to the antagonistic relationship between Mughulṭāy and his opponents and to the ensuing rivalry between them. Hence, this article seeks to examine the correlation between his personality and the rationale for his commentary, to determine the reasons behind his choice of text to write a gloss on and his sustained and harsh criticism against al-Suhaylī and his scholarly legacy. (shrink)