The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems
我们未检测到的安全故障:现代人工智能系统中隐藏的安全关键挑战的视角
机构 * Technical University of Munich(慕尼黑技术大学)
专题命中 安全评测 :safety(title,abstract);prompt injection(abstract);AI safety(abstract);分类 cs.AI、cs.CY
AI总结 研究现代人工智能系统隐藏的安全关键挑战,提出五层框架诊断隐藏风险,识别多种未被充分认识的风险模式,给出设计、治理建议及研究议程,推动人工智能安全从模型评估转向社会技术可靠性。
Comments Email by the arXiv Support Team: "Dear Gjergji, Thank you for your patience. Your appeal was accepted. You are welcome to resubmit this work at your convenience to cs.CY (cs.AI, cs.HC) Regards, arXiv Support"
Journal ref AI and Ethics (2026) 6:295, Springer Nature