Artificial Intelligence for Cyber Security Applications

Farah JEMIL is an Associate Professor at the Higher Institute of Computer Science and Telecom of Hammam Sousse (ISITCOM), Tunisia. She has completed her Ph.D. in 2010, from the National School of Computer Sciences (ENSI), Tunisia. Since 2010, she has been member of the Scientific Council of ISITCOM for 3 years (2011-2014), and Head of the Department of Computer Science at ISITCOM for 3 years (2017-2020). Her research interests include Artificial Intelligence, Cyber Security and Big Data Analysis. She has over 60 publications in reputed international journals and conferences and has presented many invited and contributed talks at international conferences. Reference: The recent report from the White House underscores the significance of Artificial intelligence (AI) and emphasizes the need for a well-defined roadmap and investment in this field. As AI transcends the realm of science fiction and takes center stage as a transformative technology, there is an immediate imperative to systematically develop and implement AI to witness its tangible impact across diverse fields of study. This presentation makes a valuable contribution to the utilization of AI in cybersecurity applications. While intrusion detection has been extensively studied in both industry and academia, cybersecurity analysts still seek enhanced accuracy and a comprehensive threat analysis to effectively safeguard their systems in the cyberspace. To achieve improvements in intrusion detection, a more comprehensive approach is recommended, involving the monitoring of security events from heterogeneous sources. By merging security events from diverse sources and leveraging data-driven learning, a more holistic perspective and a deeper understanding of the cyber threat landscape can be attained. However, a challenge arises when dealing with the sheer volume of data, as even a single event source faces significant big data challenges when considered in isolation. Incorporating more heterogeneous data sources poses even greater difficulties. Fortunately, the integration of AI and big data analysis can provide solutions to these challenges associated with heterogeneous data. The proposed approaches encompass data pre-processing and learning stages. The experimental results validate the effectiveness of these approaches in terms of accuracy and detection rate, establishing that AI can indeed yield superior outcomes within the realm of cybersecurity.