Research Publications

Our research focuses on advancing the security, governance, and resilience of AI systems. We publish technical papers, threat taxonomies, empirical studies, and industry frameworks covering GenAI, Agentic AI, MCP ecosystems, AI assurance, and AI risk management.

[1] A. Leung, R. Zhang, K. Toyoda, and S. Loh, “From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework,” arXiv:2606.03777, June 2026.
URL: https://arxiv.org/abs/2606.03777

[2] A. Leung, R. Zhang, E. Ling, K. Toyoda, and S. Loh, “The Insurability Frontier of AI Risk: Mapping Threats to Affirmative Coverage, Silent Exposures, and Exclusions,” arXiv:2605.18784, May 2026.
URL: https://arxiv.org/abs/2605.18784

[3] C.-P. Chen, K. Toyoda, A. Lai, and A. Leung, “IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection,” arXiv:2605.11868, May 2026.
URL: https://arxiv.org/abs/2605.11868

[4] T. Otsuka, K. Toyoda, and A. Leung, “AI Identity: Standards, Gaps, and Research Directions for AI Agents,” arXiv:2604.23280, April 2026.
URL: https://arxiv.org/abs/2604.23280

[5] Y. T. Shen, K. Toyoda, and A. Leung, “MCPThreatHive: Automated Threat Intelligence for Model Context Protocol Ecosystems,” arXiv:2604.13849, April 2026.
URL: https://arxiv.org/abs/2604.13849
Note: Presented at DEFCON SG Demo Labs 2026

[6] Y. T. Shen, K. Toyoda, and A. Leung, “MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems (v1.0),” arXiv:2603.18063, March 2026.
URL: https://arxiv.org/abs/2603.18063