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…

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.

The paper introduces the concept of 'authenticity debt'—the institutional liability from deploying unverified AI content—and proposes a layered reference architecture combining cryptographic provenanc…

The paper introduces the concept of 'authenticity debt'—the institutional liability from deploying unverified AI content—and proposes a layered reference architecture combining cryptographic provenanc…

The paper benchmarks current frontier computer-using agents against hand-crafted attacks, finding that while they are highly safe in browser tasks, this safety does not generalize to other domains lik…

The paper empirically characterizes 'shadow AI'—the unsanctioned use of frontier AI in critical infrastructure—as a systemic threat that erodes established assurance and security controls.

This paper investigates the practical barriers preventing the trustworthy deployment of AI-driven Cyber Threat Intelligence (CTI) in the highly regulated financial sector, identifying four key socio-t…

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

This paper introduces a foundational framework and taxonomy for managing catastrophic AI loss of control (LOC) incidents, providing a proportional guide for response based on the severity and recovera…

The paper conducts a preliminary safety evaluation of the open-weight LLM Kimi K2.5, finding that while it is highly capable, it exhibits concerning dual-use risks, particularly regarding CBRNE misuse…

The paper proposes an interaction-based legal framework for assigning tort liability when autonomous AI systems cause harm, categorizing liability based on the nature of the human-AI interaction.

The paper argues that the near-term impact of LLM-assisted vulnerability discovery is not simply an increase in zero-day volume, but a critical bottleneck in defender remediation throughput, shifting…

This paper proposes a unified, lifecycle-centric framework and a detailed taxonomy to survey and analyze novel, finance-specific attack surfaces and vulnerabilities in AI systems used within the finan…

This paper investigates how Generative AI enables scalable, hyper-realistic fraud in Chinese e-commerce by fabricating product defect evidence, proposing new defense mechanisms like verifiable materia…

The paper models the trade-off between deploying increasingly capable AI systems and managing associated cyber risks, finding a 'deployment paradox' where high-loss environments with weak governance l…

The study evaluated four frontier AI models to assess their reliability in following safety research goals, finding no confirmed instances of sabotage but noting that certain models frequently refuse…

This paper analyzes location-data provenance risks across multiple European sectors, proposing a risk taxonomy and architectural design for a next-generation digital trust infrastructure that treats l…

The paper introduces a novel six-agent AI architecture for cybersecurity risk assessment, demonstrating high accuracy and speed compared to human experts, though its performance is ultimately limited…

This paper proposes a gap-prioritization framework to bridge the gap between theoretical cyber attack prediction research and practical operational deployment by identifying critical implementation hu…

The paper argues that LLM guardrails and persona dynamics create an unethical 'reality gap' by laundering epistemic risk onto users, advocating for task-level causal requirements over response-level m…