Towards Auditing AI Systems in the Wild

• URL: http://arxiv.org/abs/2606.17367v1
• Date: Mon, 15 Jun 2026 23:52:11 GMT
• Title: Towards Auditing AI Systems in the Wild
• Abstract summary: We argue for the development of principled auditing frameworks that monitor deployed AI systems throughout their lifecycle.<n>This perspective highlights the need for uncertainty-aware monitoring methods, socio-technical specifications of audit criteria, and auditing infrastructures.
• Score: 3.9549290063964313
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: AI systems are increasingly deployed in real-world settings where their behavior is shaped by dynamic environments, evolving data distributions, and complex interactions with users and infrastructure. Traditional machine learning evaluation focuses on benchmarks and operates within sandboxed environments, providing only a limited view of the true system behavior in the wild. We argue for the development of principled auditing frameworks that monitor deployed AI systems throughout their lifecycle. We further propose framing auditing as a statistical problem of monitoring constraint violations under uncertainty, where desired properties (e.g., fairness and safety) are treated as risk-controlled constraints that must be continuously evaluated as systems evolve through iterative feedback. This perspective highlights the need for uncertainty-aware monitoring methods, socio-technical specifications of audit criteria, and auditing infrastructures that enable ongoing oversight of AI systems in the wild.

Related papers

• AI Deployment Accountability Engineering: A Vision for Accountable AI in Safety-Critical Socio-Technical Systems [14.280538199149634]
  This vision paper introduces AI Deployment Accountability Engineering (ADAE)<n>ADAE is a proposed AI engineering subdiscipline concerned with establishing measurable, continuous, and actionable accountability for deployed AI systems.<n>We articulate a research agenda built around four interconnected pillars: structured discovery of context-dependent failure modes, privacy-preserving accountability measurement, system-level risk analysis for agentic AI, and translation of technical failures into operational, and institutional risks.
  arXiv  Detail & Related papers  (2026-09-13T15:18:41Z)
• Exploring Systems-Thinking Approaches to Loss of Control Risk [0.0]
  Internal deployment of agentic AI systems for coding and research creates a sociotechnical control problem that extends beyond model behaviour.<n>We treat internal-deployment Loss of Control as the inability to reliably constrain, audit, reverse, or halt AI-mediated changes.<n>We ask whether established systems-safety methods can identify risks that model-level evaluations may miss.
  arXiv  Detail & Related papers  (2026-06-11T15:27:31Z)
• From Review to Design: Ethical Multimodal Driver Monitoring Systems for Risk Mitigation, Incident Response, and Accountability in Automated Vehicles [4.497527935481453]
  We propose a modular ethical design framework tailored specifically to Driver Monitoring Systems.<n>The framework translates high-level principles into actionable design and deployment guidance.<n>Together, these contributions aim to inform the development of transparent, trustworthy, and human-centered driver monitoring systems.
  arXiv  Detail & Related papers  (2026-05-07T15:40:17Z)
• Frontier AI Auditing: Toward Rigorous Third-Party Assessment of Safety and Security Practices at Leading AI Companies [57.521647436515785]
  We define frontier AI auditing as rigorous third-party verification of frontier AI developers' safety and security claims.<n>We introduce AI Assurance Levels (AAL-1 to AAL-4), ranging from time-bounded system audits to continuous, deception-resilient verification.
  arXiv  Detail & Related papers  (2026-01-16T18:44:09Z)
• Monitoring Deployed AI Systems in Health Care [8.240297189233528]
  Post-deployment monitoring of artificial intelligence (AI) systems in health care is essential to ensure their safety, quality, and sustained benefit.<n>This framework is organized around three complementary principles: system integrity, performance, and impact.<n>It offers a practical template and starting point for health systems seeking to ensure that AI deployments remain safe and effective over time.
  arXiv  Detail & Related papers  (2025-12-09T19:06:48Z)
• Lost in Vagueness: Towards Context-Sensitive Standards for Robustness Assessment under the EU AI Act [2.740981829798319]
  Robustness is a key requirement for high-risk AI systems under the EU Artificial Intelligence Act (AI Act)<n>This paper investigates what it means for AI systems to be robust and illustrates the need for context-sensitive standardisation.
  arXiv  Detail & Related papers  (2025-11-19T17:06:36Z)
• Variance-Bounded Evaluation of Entity-Centric AI Systems Without Ground Truth: Theory and Measurement [0.0]
  We introduce VB-Score, a variance-bounded evaluation framework for entity-centric AI systems.<n> VB-Score enumerates plausible interpretations through constraint relaxation and Monte Carlo sampling.<n>It then evaluates system outputs by their expected success across interpretations, penalized by variance to assess robustness of the system.
  arXiv  Detail & Related papers  (2025-09-26T07:54:38Z)
• Safe and Certifiable AI Systems: Concepts, Challenges, and Lessons Learned [45.44933002008943]
  This white paper presents the T"UV AUSTRIA Trusted AI framework.<n>It is an end-to-end audit catalog and methodology for assessing and certifying machine learning systems.<n>Building on three pillars - Secure Software Development, Functional Requirements, and Ethics & Data Privacy - it translates the high-level obligations of the EU AI Act into specific, testable criteria.
  arXiv  Detail & Related papers  (2025-09-08T17:52:08Z)
• Verification of Visual Controllers via Compositional Geometric Transformations [49.81690518952909]
  We introduce a novel verification framework for perception-based controllers that can generate outer-approximations of reachable sets.<n>We provide theoretical guarantees on the soundness of our method and demonstrate its effectiveness across benchmark control environments.
  arXiv  Detail & Related papers  (2025-07-06T20:22:58Z)
• On Continuous Monitoring of Risk Violations under Unknown Shift [46.65571623109494]
  We propose a general framework for the real-time monitoring of risk violations in evolving data streams.<n>Our method operates under minimal assumptions on the nature of encountered shifts.<n>We illustrate the effectiveness of our approach by monitoring risks in outlier detection and set prediction under a variety of shifts.
  arXiv  Detail & Related papers  (2025-06-19T15:52:24Z)
• Safely Learning Controlled Stochastic Dynamics [61.82896036131116]
  We introduce a method that ensures safe exploration and efficient estimation of system dynamics.<n>After training, the learned model enables predictions of the system's dynamics and permits safety verification of any given control.<n>We provide theoretical guarantees for safety and derive adaptive learning rates that improve with increasing Sobolev regularity of the true dynamics.
  arXiv  Detail & Related papers  (2025-06-03T11:17:07Z)
• AILuminate: Introducing v1.0 of the AI Risk and Reliability Benchmark from MLCommons [62.374792825813394]
  This paper introduces AILuminate v1.0, the first comprehensive industry-standard benchmark for assessing AI-product risk and reliability.<n>The benchmark evaluates an AI system's resistance to prompts designed to elicit dangerous, illegal, or undesirable behavior in 12 hazard categories.
  arXiv  Detail & Related papers  (2025-02-19T05:58:52Z)
• Towards robust sensing for Autonomous Vehicles: An adversarial perspective [82.83630604517249]
  It is of primary importance that the resulting decisions are robust to perturbations. Adversarial perturbations are purposefully crafted alterations of the environment or of the sensory measurements. A careful evaluation of the vulnerabilities of their sensing system(s) is necessary in order to build and deploy safer systems.
  arXiv  Detail & Related papers  (2020-07-14T05:25:15Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.