Workshop on Security Testing and Assurance for LLMs and Agents (STALA) 2027
Co-located with NDSS Symposium 2027
Large language models (LLMs) and AI agents are increasingly integrated into security-critical applications, introducing new attack surfaces such as jailbreaks, prompt injection, tool misuse, data poisoning, and privacy leakage. As these systems become more autonomous, systematically identifying vulnerabilities and establishing trustworthy evidence of their security become essential.
The Workshop on Security Testing and Assurance for LLMs and Agents (STALA) brings together researchers and practitioners working on vulnerability discovery, adversarial testing, defense evaluation, and security assurance for LLMs and agents. The workshop aims to advance rigorous testing methodologies, measurable security coverage, and evidence-based assurance approaches that support the secure deployment of AI systems.
The workshop features research presentations, invited keynotes, and discussions on the challenges of systematically testing and assuring LLM-based and agentic systems.
Keynote Speakers
- Ahmad-Reza Sadeghi, TU Darmstadt, Germany
- Masashi Sugiyama, RIKEN AIP / The University of Tokyo, Japan
Submissions
The call for papers is open until 11 December 2026.
Leadership
Workshop chairs and Program Committee.
Program
Find information on the keynote, the panel, and accepted paper presentations.