Events

This workshop aims to provide an in-depth understanding of emerging security challenges associated with Artificial Intelligence (AI) and Large Language Models (LLMs), with a particular focus on adversarial attacks, vulnerability assessment, and defensive strategies. Participants will explore critical security threats such as prompt injection, jailbreak attacks, data poisoning, model manipulation, and adversarial exploitation of AI-powered applications. The workshop will introduce the principles and practical methodologies of AI red teaming, security testing, vulnerability identification, and risk mitigation to evaluate the robustness and reliability of intelligent systems. Through technical discussions and hands-on demonstrations, participants will gain insights into identifying vulnerabilities, assessing potential attack surfaces, and implementing effective defence mechanisms to develop secure, resilient, and trustworthy AI systems.