~ similar to 2604.01937v1· 20 results
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…
The paper introduces ASTRAL, a multimodal LLM-driven framework that reconstructs and analyzes fragmented cyber-physical system architectures to enable comprehensive and quantitative security risk asse…
The paper analyzes UK NIS Regulations data, finding that while 29% of reported incidents are cybersecurity related, the current regulations are limited in scope compared to the volume and nature of si…
This pilot study investigates SME readiness for Zero Trust Architecture (ZTA) and proposes a realistic three-stage adoption path based on survey data from IT professionals.
This paper analyzes how a financial-technology organization operationalizes the ISO/IEC 27001:2022 standard by examining eight core security procedures, concluding that an effective ISMS requires a ti…
The paper introduces SATAM, a novel method that derives context-rich Cryptographic Bills of Materials (CBOMs) by integrating security analysis and architectural intent, significantly improving cryptog…
The paper proposes CyberAId, a hybrid multi-agent system designed to enhance cybersecurity for financial institutions by integrating specialized LLM subagents with existing SIEM/XDR telemetry, address…
The paper proposes Sovereign 2.0, a control-plane-centric model redefining cloud sovereignty as enforceable governance authority and operational control, rather than mere data location.
This cross-national review analyzed government cybersecurity guidance for smart homes, finding that while general security advice is abundant, structured, step-by-step incident response guidance is ra…
This paper reviews recent EU AI regulatory documents to clarify definitions and synthesize current provisions regarding security, privacy, and autonomous agentic AI.
The paper argues that current Software Bills of Materials (SBOMs) are fundamentally flawed due to a lack of shared understanding regarding what constitutes a 'component,' demonstrating that existing t…
The paper proposes a declarative, autonomous, self-protecting framework for securing complex 5G/6G networks by leveraging a standardized security ontology and automated graph reasoning to neutralize l…
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.
Sven Peldszus, Frederik Reiche, Kevin Hermann, Sophie Corallo +2 more
The paper maps 66 security design DSLs to 559 code-level analyzer checks to quantify the challenging relationship between high-level security design and low-level implementation vulnerabilities, revea…
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 proposes an organization-scoped LLM agent runtime architecture designed to provide an auditable, model-agnostic platform for regulated cybersecurity operations, integrating deeply with exist…
The paper proposes a novel, organization-scoped LLM agent runtime architecture designed specifically for regulated cybersecurity operations, ensuring auditable context and integration with existing se…
The paper introduces a comprehensive security framework, AgentRFC, to systematically analyze and test the security conformance of various AI agent protocols, identifying critical design gaps, especial…
The paper proposes a novel semi-automated method to perform continuous threat modeling by inferring the actual system architecture from combined static configuration and dynamic network flow data, sig…