The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems

arXiv:2607.19292v1 Announce Type: cross Abstract: Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios. That focus is incomplete. In deployed systems, many of the most consequential failures are quieter: plausible rather than spectacular, distributed across components rather than localized in a single output, and normalized by workflows before they are recognized as hazards. We argue that a central safety challenge in modern AI systems is increasingly not only whether a model emits a harmful response, but whether the broader socio-technical system preserves the conditions under which errors remain visible, contestable, containable, and recoverable. We propose a five-layer framework for diagnosing these hidden risks: (1) epistemic integrity, concerning whether evidence and uncertainty are represented honestly enough to support calibrated reliance; (2) control integrity, concerning whether authority, permissions, and action boundaries remain robust under attack and optimization; (3) temporal integrity, concerning whether safety holds across sessions, memory updates, and deployment drift; (4) organizational integrity, concerning whether institutions retain the capacity to audit, assign responsibility, and intervene effectively; and (5) ecosystem integrity, concerning whether AI systems preserve rather than erode the information environment on which future oversight depends. Across these layers, we identify under-recognized risk patterns, including overreliance, uncertainty and legitimacy laundering in retrieval, prompt injection, reward hacking, memory poisoning, evaluation deception, fictional human oversight, synthetic evidence pollution, and model collapse. We conclude with design and governance recommendations and a research agenda for shifting AI safety from model-centric evaluation toward socio-technical reliability.

Abstract:Current AI safety discourse still focuses disproportionately on visible failures, including obvious harms, dramatic misuse, and hypothetical catastrophic scenarios. That focus is incomplete. In deployed systems, many of the most consequential failures are quieter: plausible rather than spectacular, distributed across components rather than localized in a single output, and normalized by workflows before they are recognized as hazards. We argue that a central safety challenge in modern AI systems is increasingly not only whether a model emits a harmful response, but whether the broader socio-technical system preserves the conditions under which errors remain visible, contestable, containable, and recoverable. We propose a five-layer framework for diagnosing these hidden risks: (1) epistemic integrity, concerning whether evidence and uncertainty are represented honestly enough to support calibrated reliance; (2) control integrity, concerning whether authority, permissions, and action boundaries remain robust under attack and optimization; (3) temporal integrity, concerning whether safety holds across sessions, memory updates, and deployment drift; (4) organizational integrity, concerning whether institutions retain the capacity to audit, assign responsibility, and intervene effectively; and (5) ecosystem integrity, concerning whether AI systems preserve rather than erode the information environment on which future oversight depends. Across these layers, we identify under-recognized risk patterns, including overreliance, uncertainty and legitimacy laundering in retrieval, prompt injection, reward hacking, memory poisoning, evaluation deception, fictional human oversight, synthetic evidence pollution, and model collapse. We conclude with design and governance recommendations and a research agenda for shifting AI safety from model-centric evaluation toward socio-technical reliability.

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"

Computers and Society (cs.CY); Artificial Intelligence (cs.AI); Human-Computer Interaction (cs.HC)

arXiv:2607.19292 [cs.CY]

(or arXiv:2607.19292v1 [cs.CY] for this version)

https://doi.org/10.48550/arXiv.2607.19292 arXiv-issued DOI via DataCite (pending registration)

https://doi.org/10.1007/s43681-026-01132-0 DOI(s) linking to related resources

From: Gjergji Kasneci Prof. Dr. [view email] [v1] Tue, 21 Jul 2026 17:02:37 UTC (12,119 KB)

aiqbench analysis

The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems

Related coverage