Workshop All Audiences 3 Hours 10:15 - 13:00 August 08, 2026

Mohammed Ilyas Ahmed

Prompt injection has rapidly emerged as one of the most critical and least understood vulnerabilities in modern application security. As organizations race to integrate LLMs into customer-facing products, internal tools, and autonomous agents, attackers are already exploiting these systems in ways traditional security controls were never designed to catch. This one-day, hands-on training gives attendees a thorough, practical understanding of prompt injection — from basic chatbot manipulation to sophisticated attacks against RAG pipelines and autonomous AI agents. Using a purpose-built lab environment, attendees will exploit real vulnerabilities in LLM-powered applications, understand exactly why they work, and then build effective defenses against them. The course is structured as an attack-first, defend-second journey. By experiencing these vulnerabilities as an attacker, attendees leave with deep intuition about where AI systems.

Mohammed Ilyas Ahmed

Making the Unachievable Achievable | Speaker | Author | Reviewer | Host | OWASP Contributor

I am a seasoned security and DevSecOps professional with deep expertise in helping organizations strengthen their security posture across modern, cloud-native environments.

I am an active contributor to the global technology community and a frequent speaker at leading industry conferences and platforms, including DEF CON, Black Hat, KubeCon (Paris), ISACA, IANS, and Wallarm, among others. I am also regularly invited to serve as a technical session judge.

publishing work that advances discussions around modern security practices, governance, and risk management. I am also a distinguished member of the Harvard Business Review Advisory Council.

My work has a global reach through my role as a Member of the Global Advisory Board at VigiTrust Limited (Dublin, Ireland).

I am the author of Cloud-Native DevOps, a practical guide to building scalable, reliable, and secure cloud-native applications.