Foundations of Language Model Security: Theory, Practice, and Fundamental Limits

The workshop studies foundational reasons for language-model security vulnerabilities. Researchers connect prompt injection, poisoned data and the interaction between model and classical software weaknesses, seeking principled approaches to building systems whose security can be understood and evaluated. Session: 08:30–18:30 (Europe/Paris). A paid NeurIPS virtual pass includes workshop livestreams; on-site access follows the host-location registration rules.