Dr Deepak Kumar Panda

Background

Dr Deepak Kumar Panda works in the areas of secure autonomous systems, artificial intelligence, and adversarial AI at Cranfield University. His research focuses on understanding and improving the security, robustness, and resilience of AI-enabled autonomous systems operating in complex and potentially adversarial environments. His research interests include adversarial machine learning, trustworthy and secure AI, autonomous systems security, cyber-physical systems, and the development of resilient AI-based decision-making approaches. A particular focus of his work is identifying vulnerabilities in intelligent and autonomous systems and developing methods to strengthen their robustness against adversarial manipulation, uncertainty, and emerging security threats. Through his research, Deepak aims to contribute to the development of autonomous and AI-enabled systems that are not only capable and adaptive, but also secure, trustworthy, and resilient when deployed in safety- and security-critical environments.

Research opportunities

My research interests lie at the intersection of artificial intelligence, cybersecurity, and autonomous systems, with a particular focus on developing secure, trustworthy, and resilient AI-enabled autonomy.

Key areas of interest include:

- Secure and resilient autonomous systems.

- AI security and vulnerability assessment

- Cybersecurity of autonomous and cyber-physical systems

- Attack and defence strategies for AI-enabled systems

- Safety, assurance, and resilience of intelligent autonomous systems

- AI red teaming and evaluation of autonomous systems

My broader research objective is to understand how intelligent and autonomous systems behave when exposed to deliberate attacks, uncertainty, and unexpected operating conditions, and to develop methods that enable these systems to remain secure, reliable, and trustworthy in safety- and security-critical applications.

Current activities

Deepak Kumar Panda is currently engaged in research on secure and resilient autonomous systems, with a particular emphasis on adversarial AI and the security of AI-enabled autonomous technologies.

His current work investigates the vulnerabilities of intelligent and autonomous systems to adversarial threats and explores approaches for improving their robustness, resilience, and trustworthiness. This includes examining how adversarial manipulation can affect AI-based perception, reasoning, and decision-making, as well as developing methods for evaluating and mitigating such risks.

His research also considers the broader challenges associated with deploying AI and autonomous systems in safety- and security-critical environments, including AI assurance, adversarial robustness, system resilience, and the evaluation of emerging AI security threats.

Clients

• Thales SA
• SAAB AB
• NATS Holdings

Publications

• Articles in journals
• Conference papers