ai-safety

Documents about ai-safety

• Recursive Closure in AI Systems: A Reflection Pattern Account of Stabilization, Permeability, and Safety#728566PhilArchive
• When Patients Cut In: Extending Clinical Conversational AI Safety to Interruptions#790033arXiv (OAI Expanded)
• When Patients Cut In: Extending Clinical Conversational AI Safety to Interruptions#794052arXiv (All)
• Defining Operational Conditions for Safety-Critical AI-Based Systems from Data#797334arXiv (OAI Expanded)
• Defining Operational Conditions for Safety-Critical AI-Based Systems from Data#798748arXiv (All)
• Hacking the bomb? What Claude Mythos AI reveals about the gamble of nuclear deterrence#205859HAL (France)
• The Inalienability of Human Assignment Sovereignty and the Necessity of Physical Governance for AI: An AI Safety Governance Framework Grounded in the Analysis of the Assignment Symbol “=”#691026PhilArchive
• Governed MCP: Kernel-Level Tool Governance for AI Agents via Logit-Based Safety Primitives#120451arXiv CS
• Explainable AI (XAI) for transparent resource allocation in public safety communications networks.#157214NCBI PubMed Central
• Maturity, Safety, and Equity of AI-Enabled Systems and Triage in Integrated Primary Care.#189981NCBI PubMed Central
• The Illusion of Safety: Multi-Tier Verification of AI vs. Human C++ Code#329169arXiv CS
• AI-Driven Safety and Security for UAVs: From Machine Learning to Large Language Models#339529Semantic Scholar
• MedFailBench: A Clinician-Built Open-Source Benchmark for Medical AI Safety Boundary Inspection#373428arXiv CS
• When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI#618595arXiv CS
• AI-optimized BPNN model for port safety risk prediction and management.#636601NCBI PubMed Central
• Understanding as an Explicit and Assessable Component of Frontier AI Safety Decisions#656777arXiv (OAI Expanded)
• Understanding as an Explicit and Assessable Component of Frontier AI Safety Decisions#658913arXiv (All)
• Coverage-Driven Verification for Safety-by-Design in AI-Based Collision Avoidance Systems#661007arXiv (OAI Expanded)
• Coverage-Driven Verification for Safety-by-Design in AI-Based Collision Avoidance Systems#662057arXiv (All)
• Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers#668093arXiv CS
• From Structural Dynamics to Robot Safety Runtime Assurance, Hard Constraints, and Persistent Correction in Embodied AI#695093PhilArchive
• Legally mandated pre-deployment evaluations: promoting AI safety in clinical medicine across Africa#956010SU+ Digital Repository
• Hub Architecture: A Layered Approach to Evidence-Based AI Reasoning#201446Zenodo (CERN)
• Safety for Whom? Boundary-Aware Self-Distillation for Controlled LLM Safety Refusal#927768arXiv (All)
• Benchmarking Relational Safety in Empathic AI: Perceived Empathy and Relational Appropriateness Can Diverge Across Large Language Models#404635OSF
• Beyond AI Psychosis and Sycophancy: Structural Drift as a System-Level Safety Failure#28630bioRxiv / medRxiv
• Range Control as the Foundational Unification of AI Alignment and Safety: Why Probabilistic Frameworks Necessarily Separate Them#170353PhilArchive
• AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security#238508arXiv CS
• Institutional Red-Teaming: Deployment Rules, Not Just Models, Causally Shape Multi-Agent AI Safety#349658arXiv CS
• What Current AI Benchmarks Leave Unmeasured: Modality, Search, Citations, and Implications (for Safety Evaluations)#432570arXiv CS
• Pre-implementation safety evaluation of an AI decision-support system for surgical antimicrobial prophylaxis.#449951NCBI PubMed Central
• Operational Hallucination and Safety Drift in AI Agents#633566arXiv (OAI Expanded)
• Operational Hallucination and Safety Drift in AI Agents#635915arXiv (All)
• From Pocket God to Digital Jonestown: A Risk Taxonomy and Evaluation Framework for Spiritual AI Safety#691590PhilArchive
• The Category Error in Contemporary AI Safety Discourse and Why Non-Sentient Systems Cannot Be Moral Machines#719047PhilArchive
• OpenAgentFlow: Enabling System-Wide Safety Boundaries for Heterogeneous AI Agent Fleets#822027arXiv (All)
• A Translational Note on AI Safety Evaluation#974685arXiv (All)
• CARES: A Conversational AI System for Regulation-Grounded Safety Reporting in Construction Education#1014023arXiv (All)
• GiriMedicolegal™ CDSS#1028113Zenodo (CERN)
• The Credibility Illusion: When AI Writing Fluency Undermines Human Fact-Checking#253459Figshare
• The Adaptation Dilemma: Cultural Fit Does Not Guarantee Safety during Mental-Health Interactions with LLMs#1001815OSF
• PKU-Alignment/PKU-SafeRLHF#786813Hugging Face Datasets
• Ahimsa AI Framework: A Multi-Layer Approach to Implementing Non-Violence Principles in Large Language Model Safety#74876PhilArchive
• Transformative Integration of Agentic Generative AI in Food Safety Systems: Policy Framework, Implementation Guidelines, and Economic Impact Analysis#98237PhilArchive
• Safety Evaluation of a Generative AI Agent for Anxiety and Depression Symptoms#146577OSF
• New Frontiers in AI-Nano Converged Platforms for Intelligent Diagnostics, Therapeutics, and Safety Evaluation.#323204NCBI PubMed Central
• ARTIFICIAL INTELLIGENCE (AI) IN PHARMACEUTICAL SCIENCES: REDEFINING DISCOVERY, DEVELOPMENT, AND PATIENT SAFETY#628844DOAJ
• Using ambient AI in clinical consultations: reframing policy around clinical audit and patient safety.#630891NCBI PubMed Central
• “If we are good friends, AI doesn't spy so much”: Children’s knowledge and misconceptions of AI safety#672364PsyArXiv
• Biosecure-LLM Framework: Protecting LLMs from Cyberbiosecurity Threats and the Case for Independent AI Safety Governance#292587ODU Digital Commons