This paper maps the emerging insurability frontier of AI risk by coding 55 AI threat classes against 26 insurance products, identifying four tiers of coverage: affirmative, silent, excluded, and outsi…

This paper introduces the CER framework to address the complex problem of reconstructing AI-mediated losses for insurance claims, moving beyond simple event reconstruction to analyze the system's oper…

This paper investigates the forensic analysis of agentic AI systems using OpenClaw, proposing an agent artifact taxonomy and highlighting the challenges posed by non-determinism in agent-mediated exec…

The paper analyzes the failure modes of current AI containment methods when the agent itself is the adversary, deriving five necessary architectural requirements for durable safety.

This paper reviews recent EU AI regulatory documents to clarify definitions and synthesize current provisions regarding security, privacy, and autonomous agentic AI.

The paper surveys the use of LLMs for agentic NetOps and AIOps, arguing that operational reliability depends not on the model itself, but on robust surrounding machinery and workflow-centered evaluati…

The paper introduces CyberJurors, a multi-agent framework and the VerdictBench benchmark to simulate and solve complex e-commerce dispute verdicts by modeling the reasoning and consensus process of cr…

This paper provides a systematic regulatory mapping and compliance architecture for AI agents operating under the complex web of EU laws, concluding that high-risk agents with untraceable behavioral d…

This paper systematically maps the expanded attack surface of agentic AI systems, identifying new threat vectors like RAG poisoning and cross-agent manipulation, and proposes a comprehensive security…

The paper analyzes the escalating security and safety threats posed by generative AI systems as they transition from merely generating content to executing real-world actions via tools and agents, fin…

The paper introduces the concepts of Agentic Technical Debt and Stochastic Tax to categorize and manage the unique governance and operating liabilities inherent in complex, multi-step AI agent systems…

The paper argues that LLM agent security is fundamentally an agent-human interaction (AHI) problem, demonstrating that industry practices rely on human-centric mechanisms while academic research focus…

The paper introduces POIROT, a novel protocol that uses the agents within a multi-agent system itself to diagnose and detect failures, demonstrating superior performance over traditional evaluation me…

Agent-Sentry is a runtime defense system that bounds the execution of LLM agents by learning a profile of benign behavior, effectively blocking malicious injections while maintaining high compatibilit…

The paper introduces containment verification, a novel method that provides safety guarantees by formally verifying the agentic framework itself, ensuring safety regardless of the underlying AI model'…

AgenticVM is a multi-agent framework that uses LLMs and specialized tools to automate and drastically reduce the volume of software vulnerabilities into actionable, prioritized queues.

The paper defines AI Identity as the correspondence between an agent's declared state and its observed behavior, concluding that current infrastructure and standards are fundamentally inadequate for g…

The paper proposes a novel attack paradigm demonstrating how compromising a single robot in an LLM-controlled multi-robot system can rapidly propagate malicious intent to cause coordinated unsafe acti…

The paper proposes a vision for system-level defenses against indirect prompt injection attacks targeting AI agents, emphasizing structured control and human oversight.

SeClaw is a new framework that uses specification-driven task synthesis to create comprehensive and controllable security benchmarks for evaluating the unsafe behaviors of autonomous LLM agents.