The World AI Security conference 2026 (seclab.stanford.edu)

The inaugural World AI Security Conference, set for 2026 at Stanford University, aims to address the escalating cybersecurity challenges posed by the rapid growth of AI systems. With a focus on the entire AI pipeline—from training to inference—this annual event will bring together leading academic researchers and industry practitioners. Participants will explore pressing topics such as emerging attack techniques and robust defense strategies, discussing the most significant AI security findings from the past year. This conference holds particular importance for the AI/ML community as it highlights the necessity of securing AI technologies in an increasingly digital landscape. By fostering collaboration and dialogue among experts from diverse backgrounds, the event aims to advance the development of effective security measures, ensuring the reliability and trustworthiness of AI applications. The Stanford Security Lab is organizing the event, underscoring the commitment to addressing these vital issues within both academic and practical domains.