Dr Mohammed Al-Khalidi

Speaker

Associate Professor in Cyber Security at the Department of Computing and Mathematics, Manchester Metropolitan University, UK.

Dr Mohammed Al-Khalidi is an Associate Professor in Cyber Security at the Department of Computing and Mathematics, Manchester Metropolitan University, Manchester, UK. He has more than 18 years of academic and industrial experience in the fields of Networking, Security, and AI. He has been awarded research funding by UKRI’s Global Challenges Research Fund and other government bodies focussing on AI Security and Network Security. He has also been involved in EU projects, including POINT (awarded best Internet project by the Future Internet Assembly). His past assignments include Lecturer with the Department of Computer Science, Edge Hill University, and Research Officer with the School of Computer Science and Electronic Engineering, University of Essex, UK, where he also received his PhD degree. Prior to that, he worked in industry as a Senior Core Network Engineer at several leading mobile telecommunication companies. His research interests include AI security, IoT security, Mobile Computing, Cloud Computing, Ad-Hoc Networks, and Information Centric Networks.

Title of the Talk: Are AI systems intelligent enough to protect us from cyber attacks?

Abstract: AI systems are transforming various aspects of modern life in areas such as healthcare, transportation, education, and finance among many others. They also play a crucial role in enhancing cybersecurity measures, but it’s important to understand that they are not a panacea. As AI systems expand into different applications, they can result in an increase in adversarial attacks. While AI technologies have shown promise in detecting and preventing cyber-attacks, they also have various limitations. Adversarial attacks can exploit vulnerabilities within AI models and corrupt the data that AI models learn from, causing these models to generate inaccurate outputs. When these AI models are applied to real-world scenarios, inaccuracies can be fatal, making adversarial attacks very dangerous. This talk will shed some light on the key security challenges associated with the widespread use of AI systems, and the appropriate countermeasures that can be applied guided by past research experience in the field.

Speaker