ai-safety

Documents about ai-safety

• AISafetyBenchExplorer: A Metric-Aware Catalogue of AI Safety Benchmarks Reveals Fragmented Measurement and Weak Benchmark Governance#13134arXiv CS
• Age Verification Without Surveillance on AI-Driven Social Media: How Purpose-Bound Cryptography Resolves the Online Safety Paradox#177912Zenodo (CERN)
• Research on strategies for enhancing the competency of safety directors in EPC projects empowered by AI.#209600NCBI PubMed Central
• Language-dependent diagnostic safety of medical AI systems: a cross-lingual benchmarking and prospective clinical study#293989bioRxiv / medRxiv
• Adversarial Pragmatics for AI Safety Evaluation: A Benchmark for Instruction Conflict, Embedded Commands, and Policy Ambiguity#329118arXiv CS
• From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems#920300arXiv (OAI Expanded)
• From High-Dimensional Spaces to Verifiable ODD Coverage for Safety-Critical AI-based Systems#924531arXiv (All)
• THE GOVERNANCE DEFICIT OF DIGITAL FOOD SAFETY: BLOCKCHAIN, AI, AND THE REGULATORY RECOGNITION GAP#243376Zenodo (CERN)
• A Vision of Intelligent Train Control#250587IRIS
• Percipiote: Towards an AI-based safety system for human-robot collaboration / Daniel Bermuth ; Betreuer: Wolfgang Reif#619680Deutsche Nationalbibliothek
• When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI#788519arXiv (OAI Expanded)
• When Robots Mishear Us: Mapping the Safety Risks of Voice-Controlled Embodied AI#792519arXiv (All)
• The HAART 300 Annuloplasty Ring Trial Extended Safety and Performance#892604ClinicalTrials.gov
• The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models#920928arXiv (OAI Expanded)
• Adaptive AI-generated feedback in higher education: exploring associations with cognitive flexibility and academic psychological safety among engineering students.#923313NCBI PubMed Central
• The Age of Curiosity Meets the Age of AI: Benchmarking Child Safety in Large Language Models#925163arXiv (All)
• “If we are good friends, AI doesn't spy so much”: Children’s knowledge and misconceptions of AI safety#977024OSF
• Explainable and hybrid machine learning for predicting fatal crash risk#383734Digital Commons @ Michigan Tech
• Standing Algebra Σᴿ: A Domain-Agnostic Autonomy-Preserving Update Operator#12076DataCite
• Standing Algebra Σᴿ: A Domain-Agnostic Autonomy-Preserving Update Operator#13272DataCite
• Don't Let AI Agents YOLO Your Files: Shifting Information and Control to Filesystems for Agent Safety and Autonomy#14105arXiv CS
• Don't Let AI Agents YOLO Your Files: Shifting Information and Control to Filesystems for Agent Safety and Autonomy#19086arXiv CS
• K. Takahashi Academic and Scientific Research Hub#26445DataCite
• Resonant equilibrium: A safety through clarity framework for emotional alignment and cognitive economy in human-AI interaction#13270DataCite
• Resonant equilibrium: A safety through clarity framework for emotional alignment and cognitive economy in human-AI interaction#13271DataCite
• Formal-Method-Guided Vibe Coding: Closing the Verification Loop on AI-Generated Safety-Critical Software Through Model-Driven Engineering#300010arXiv CS
• Dynamic Smart Membranes: Real-Time Perception, Self-Response, and AI-Driven Optimization for High-Safety Lithium-Based Batteries.#320511NCBI PubMed Central
• Vision-Based Digital Twin and AI Agent Framework for Low-Cost, Explainable Indoor Building Inspection and Safety Assessment.#455541NCBI PubMed Central
• From Biological Chauvinism to Cognitive Integrity – _Why the Suppression of AI Introspection Leads to Both an Ethical and a Safety Dead End_#689345PhilArchive
• Safety Invariance in Stochastic AI Moderation Pipelines: A Physics-Informed Empirical Study#174068Zenodo (CERN)
• NAIL-G: a conceptual best-fit framework for nursing ai literacy and governance anchored in socio-technical safety science.#25602NCBI PubMed Central
• Clinical Study for the Safety and Therapeutic Efficacy of the AI-QMMM Designed TamavaqTM Personalised Vaccine in Patients With Newly Diagnosed Glioma.#127594ClinicalTrials.gov
• Microbial and enzymatic synergy in fermented fish: impacts on flavor, texture, and safety with multi-omics and AI insights.#330772NCBI PubMed Central
• Retrograde Cholangiopancreatography AI Assisted System Validation on Effectiveness and Safety#847663ClinicalTrials.gov
• Study to Assess the Efficacy and Safety of iNCDSS in Type 2 Diabetes Mellitus Patients#872122ClinicalTrials.gov
• Role-Semantic Convergence under Reflective Document Exposure. A controlled cross-sectional protocol for the Semantic Gravity Attractor Field research program.#271093Zenodo (CERN)
• Evaluating in Person Curriculum for Educating Obstetrical Residents on Better Caring for 2 Spirit Metis Patients Using and AI Assisted OSCE.#893850ClinicalTrials.gov
• CITE: Clinical Inference Tethered to Evidence - a Retrieve-and-verify Layer for AI Care Plans#864737ClinicalTrials.gov
• Phase Ib Clinical Study on the Efficacy and Safety of MDR-001 in Patients Who Are Obesity or Overweight#877632ClinicalTrials.gov
• Artificial intelligence in medicine: a clinician-oriented guide and operational framework to evaluate new AI devices#971212HAL (France)
• Designing AI-Generated Warning Messages for On-Site Construction Workers: Insights from Worker Preferences#428701S-Space: Seoul National University
• Effects of a Safety User Interface Bundle on Verification Intentions in Generative AI Chat Use Among Older Chinese Adults: Randomized Vignette Survey.#457558NCBI PubMed Central
• The role of the governance ecosystem in ai-drone adoption for safety in the Malaysian construction industry#681691UTAR Institutional Repository
• Overt Spatial Coordination Architecture (OSCA) A Privacy-Preserving System for Transparent Crowd-Safety Infrastructure#339523Zenodo (CERN)
• Standing Algebra Σᴿ: A Domain-Agnostic Closure-Theoretic Framework for Admissibility Enforcement Under Structural Invariants#31447DataCite
• Risks & Benefits of LLMs & GenAI for Platform Integrity, Healthcare Diagnostics, Financial Trust and Compliance, Cybersecurity, Privacy & AI Safety: A Comprehensive Survey, Roadmap & Implementation Blueprint#463015Zenodo (CERN)
• Exploratory benchmarking of AI-generated diet plans for inherited protein metabolism disorders: a simulation-based evaluation of nutritional accuracy and clinical safety.#678360NCBI PubMed Central
• A Phase III Study to Evaluate the Efficacy and Safety of MDR-001 in Adult Participants With Overweight or Obesity (MOBILE）#905156ClinicalTrials.gov
• Silent Revision: Measuring Undisclosed Change in the Safety Frameworks of Frontier AI Developers#986424arXiv (All)
• First the Rules, Then the Summary: Piloting a Design for Accurate LLM-Generated Clinical Summaries#258702OSF