Jason Stanley
Head of Applied AI Research
AI Research Leadership
Jason Stanley is Head of Applied AI Research at ServiceNow, working with teams to de-risk emerging AI capabilities and controls. His work centers on the governance, security, and evaluation of AI agents in the enterprise, and on how organizations can give agents meaningful autonomy while keeping risk under control. He has served on AI working groups at the OECD, the Partnership on AI, and MLCommons, worked as a policy advisor for the Government of Canada, and writes and speaks regularly on AI governance and security. A Rhodes Scholar, he holds a Ph.D. in Sociology from New York University.
Publications
The Observability Gap in AI Multi-agent Systems.
Workshop at the Neural Information Processing Systems (NeurIPS),
2026.
Societal Alignment Frameworks Can Improve LLM Alignment.
ACM Conference on Fairness, Accountability, and Transparency,
2026.
Malice in Agentland: Down the Rabbit Hole of Backdoors in the AI Supply Chain.
ACM Conference on AI and Agentic Systems,
2026.
No, of Course I Can! Deeper Fine-Tuning Attacks That Bypass Token-Level Safety Mechanisms.
International Conference on Learning Representations,
2026.
DoomArena: A framework for Testing AI Agents Against Evolving Security Threats.
Conference on Language Modeling (COLM),
2025.
DoomArena: A framework for Testing AI Agents Against Evolving Security Threats.
Workshop at the International Conference of Machine Learning (ICML),
2025.
Silent Sabotage: Injecting Backdoors into AI Agents Through Fine-Tuning.
Workshop at the International Conference of Machine Learning (ICML),
2025.
Societal Alignment Frameworks Can Improve LLM Alignment.
Workshop at the International Conference of Learning Representation (ICLR),
2025.
LitLLMs, LLMs for Literature Review: Are We There Yet?.
Transactions on Machine Learning Research (TMLR),
2025.