Safety Critical Domain

Safety-critical domains encompass applications where system failures can have severe consequences, demanding high reliability and trustworthiness. Current research focuses on improving the safety and reliability of AI-powered systems within these domains, particularly addressing challenges posed by the inherent uncertainties of machine learning models like deep neural networks and large language models. Key areas of investigation include developing robust training datasets, incorporating domain knowledge to guide safe exploration, and implementing verification and shielding techniques to mitigate risks. This work is crucial for enabling the safe and responsible deployment of AI in high-stakes applications such as aviation, healthcare, and autonomous driving.