Purpose and Scope

In recent years, artificial intelligence (AI) has achieved great success in intelligent transport, smart manufacturing, smart healthcare, business, smart cities, modern power systems, social media and many other areas. These achievements have been made possible by AI systems powered by machine learning and deep learning algorithms. However, these systems can be vulnerable to adversarial attacks and lack transparency, leading to significant concerns about their security and reliability.

Recent literature shows that small changes in image, text, audio and network data can cause significant errors in well-trained AI models. Therefore, security concerns arising from the vulnerability of AI models need to be investigated and addressed. In addition, the need for Explainable Artificial Intelligence (XAI) has become increasingly important to ensure transparency, reliability and accountability of AI systems. XAI aims to make the decision-making processes of AI models understandable to humans and to increase the overall safety and reliability of these systems.

This special session aims to bring together the latest available research on AI safety and reliability, XAI and their applications.

The main topics of the special session include, but are not limited to, the following

• – The problem of security, privacy and reliability in artificial intelligence models
• – Explainable artificial intelligence techniques and frameworks
• – Evaluation metrics for explainability and transparency in artificial intelligence systems
• –Counterattacks and defenses in the Internet of Things / Cyber-physical systems
• – Applications of explainable artificial intelligence in industry and research
• – Artificial intelligence applications in autonomous driving, smart manufacturing, healthcare, smart building, etc. for privacy and reliability