10 papers
Revoked but Still Authoritative: An Empirical Study of Revocation Enforcement in Agent-Memory Systems
Yi Ting Shen, Kentaroh Toyoda, Alex Leung
Long-running language-model agents depend on persistent memory. Many agent-memory systems preserve history through soft revocation: a contradicted fact is marked invalid and retain…
ACEA: An Adversarial Co-Evolution Arena for Head-to-Head Red-Team and Blue-Team LLM Testing
Yi Ting Shen, Kentaroh Toyoda, Alex Leung
Automated red-team attacks and blue-team defenses for large language models (LLMs) are advancing quickly. However, attackers and defenders are built and tested in isolation, and th…
AMT-X: Phase-Structured Multi-Turn Red-Teaming with Checklist-Gated Evaluation
Yi Ting Shen, Kentaroh Toyoda, Alex Leung
Safety evaluation of large language models (LLMs) relies largely on single-turn attack datasets and single-judge scoring, underestimating risk from adaptive multi-turn adversaries…
The 2026 Singapore Consensus on Global AI Safety Research Priorities
Stephen Casper, Oskar Galeev, Yoshua Bengio +117
Frontier AI capabilities and autonomy are advancing rapidly. A growing number of real-world incidents make a trusted AI ecosystem essential to embracing AI with confidence. The 202…
The Insurability Frontier of AI Risk: Mapping Threats to Affirmative Coverage, Silent Exposures, and Exclusions
Alex Leung, Rex Zhang, Ervin Ling +2
The rapid diffusion of agentic AI has created a new coverage problem for commercial insurance: some AI-mediated losses are now affirmatively insured, some create silent-AI exposure…
From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework
Alex Leung, Rex Zhang, Kentaroh Toyoda +1
AI losses that arise through an insured organization's generative or agentic AI system require state reconstruction, not merely event reconstruction, because the relevant state cha…
IPI-proxy: An Intercepting Proxy for Red-Teaming Web-Browsing AI Agents Against Indirect Prompt Injection
Chia-Pei, Chen, Kentaroh Toyoda +2
Web-browsing AI agents are increasingly deployed in enterprise settings under strict whitelists of approved domains, yet adversaries can still influence them by embedding hidden in…
AI Identity: Standards, Gaps, and Research Directions for AI Agents
Takumi Otsuka, Kentaroh Toyoda, Alex Leung
AI agents are now running real transactions, workflows, and sub-agent chains across organizational boundaries without continuous human supervision. This creates a problem no curren…
MCPThreatHive: Automated Threat Intelligence for Model Context Protocol Ecosystems
Yi Ting Shen, Kentaroh Toyoda, Alex Leung
The rapid proliferation of Model Context Protocol (MCP)-based agentic systems has introduced a new category of security threats that existing frameworks are inadequately equipped t…
MCP-38: A Comprehensive Threat Taxonomy for Model Context Protocol Systems (v1.0)
Yi Ting Shen, Kentaroh Toyoda, Alex Leung
The Model Context Protocol (MCP) introduces a structurally distinct attack surface that existing threat frameworks, designed for traditional software systems or generic LLM deploym…