Daniyal Naeem is an experienced Cybersecurity Professional with extensive expertise in cyber threat research, specialising in complex cybercriminal and nation-state threat actors. He has built and led global Cyber Incident Response and Threat Intelligence programmes, strengthening organisational resilience against advanced and evolving threats. Daniyal also brings expertise in the security, governance, and risk management of emerging technologies, including Artificial Intelligence, agentic AI systems, and AI-enabled security tooling. His work focuses on secure-by-design AI architectures, AI risk management, adversarial threat modelling, and the security of AI orchestration frameworks and data flows. He actively contributes to industry collaboration and standards initiatives, including ETSI and GSMA Fraud and Security Group (FASG) working groups, as well as broader cross-sector engagement through organisations such as TechUK. He is a critical thinker, MITRE contributor, astute problem solver, and an effective translator between technical and non-technical stakeholders, with a strong focus on aligning security strategy, operational resilience, and emerging technology governance. He holds a Master's degree in Information Security from Royal Holloway, University of London and is CISSP, CISM, and CCSP certified.
Model Context Protocol (MCP) is rapidly becoming the backbone of agentic AI, connecting models to tools, memory, plugins, and live data. But it introduces a critical security failure: it collapses trust boundaries. Trusted system instructions, user input, and external data all merge into a single prompt the model cannot reliably interpret or defend. The result is a new, highly exploitable layer, where prompt injection, tool spoofing, and data leakage happen inside the model's execution flow, beyond the reach of traditional controls. In this session, Daniyal Naeem, Principal Security Authority-AI, at BT Group shows how to restore trust boundaries in MCP-based agent systems: separating trusted and untrusted context, validating tools and data before model exposure, and enforcing identity, permissions, isolation, and audit controls across every MCP flow.
Check out the incredible speaker line-up to see who will be joining Daniyal.
Download The Latest Agenda