Where AI Assurance Might Go Wrong: Initial lessons from engineering of critical systems

• URL: http://arxiv.org/abs/2502.03467v1
• Date: Tue, 07 Jan 2025 22:02:23 GMT
• Title: Where AI Assurance Might Go Wrong: Initial lessons from engineering of critical systems
• Abstract summary: Critical systems perspective might support the development and implementation of AI Safety Frameworks.<n>We consider four key questions: What is the system? How good does it have to be?<n>We advocate the use of assurance cases based on Assurance 2.0 to support decision making in which the criticality of the decision as well as the criticality of the system are evaluated.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: We draw on our experience working on system and software assurance and evaluation for systems important to society to summarise how safety engineering is performed in traditional critical systems, such as aircraft flight control. We analyse how this critical systems perspective might support the development and implementation of AI Safety Frameworks. We present the analysis in terms of: system engineering, safety and risk analysis, and decision analysis and support. We consider four key questions: What is the system? How good does it have to be? What is the impact of criticality on system development? and How much should we trust it? We identify topics worthy of further discussion. In particular, we are concerned that system boundaries are not broad enough, that the tolerability and nature of the risks are not sufficiently elaborated, and that the assurance methods lack theories that would allow behaviours to be adequately assured. We advocate the use of assurance cases based on Assurance 2.0 to support decision making in which the criticality of the decision as well as the criticality of the system are evaluated. We point out the orders of magnitude difference in confidence needed in critical rather than everyday systems and how everyday techniques do not scale in rigour. Finally we map our findings in detail to two of the questions posed by the FAISC organisers and we note that the engineering of critical systems has evolved through open and diverse discussion. We hope that topics identified here will support the post-FAISC dialogues.

Related papers

• The safety failures we are not instrumenting: a perspective on hidden safety-critical challenges in modern AI systems [26.594498540217568]
  In deployed systems, many of the most consequential failures are quieter than spectacular, distributed across components rather than localized in a single output, and normalized by ecosystem before they are recognized as hazards.<n>We argue that a central safety challenge in modern AI systems is not only whether a model emits harmful response, but whether the broader socio-technical system preserves the conditions under which errors remain visible, contestable, containable, and recoverable.
  arXiv  Detail & Related papers  (2026-07-21T17:02:37Z)
• Towards trustworthy agentic AI: a comprehensive survey of safety, robustness, privacy, and system security [57.35851886874902]
  Agentic AI systems execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that challenge trustworthiness.<n>This survey provides a focused examination of trustworthy agentic AI through two core dimensions that are critical for high-risk deployments.<n>For each dimension, we clarify key concepts, identify where risks emerge along the agent workflow, and summarize stage-targeted mitigation strategies.
  arXiv  Detail & Related papers  (2026-05-17T10:26:37Z)
• 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)
• Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems [2.28126966226433]
  Demonstrating the safety of autonomous systems rigorously is critical for their responsible adoption.<n>OOD detection is receiving increased attention from the research, development and safety engineering communities.<n>This comprehensive review analyses OOD detection techniques within the context of safety assurance for autonomous systems.
  arXiv  Detail & Related papers  (2025-10-24T08:38:01Z)
• Never Compromise to Vulnerabilities: A Comprehensive Survey on AI Governance [211.5823259429128]
  We propose a comprehensive framework integrating technical and societal dimensions, structured around three interconnected pillars: Intrinsic Security, Derivative Security, and Social Ethics.<n>We identify three core challenges: (1) the generalization gap, where defenses fail against evolving threats; (2) inadequate evaluation protocols that overlook real-world risks; and (3) fragmented regulations leading to inconsistent oversight.<n>Our framework offers actionable guidance for researchers, engineers, and policymakers to develop AI systems that are not only robust and secure but also ethically aligned and publicly trustworthy.
  arXiv  Detail & Related papers  (2025-08-12T09:42:56Z)
• A Systematic Mapping Study on Software Architecture for AI-based Mobility Systems [0.5156484100374057]
  We aim to provide the missing overview of existing architectures, their contribution to safety, and their level of maturity in AI-based safety-critical systems.<n>From a set of 1,639 primary studies, we selected 38 relevant studies dealing with safety assurance through software architecture in AI-based safety-critical systems.<n>The selected studies were then examined using various criteria to answer the research questions and identify gaps in this area of research.
  arXiv  Detail & Related papers  (2025-06-02T12:29:54Z)
• 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. 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)
• Safety Cases: A Scalable Approach to Frontier AI Safety [2.5005109646414017]
  We argue that writing and reviewing safety cases would substantially assist in the fulfilment of the Frontier AI Safety Commitments. We outline open research questions on the methodology, implementation, and technical details of safety cases.
  arXiv  Detail & Related papers  (2025-02-05T22:59:53Z)
• Open Problems in Machine Unlearning for AI Safety [61.43515658834902]
  Machine unlearning -- the ability to selectively forget or suppress specific types of knowledge -- has shown promise for privacy and data removal tasks. In this paper, we identify key limitations that prevent unlearning from serving as a comprehensive solution for AI safety.
  arXiv  Detail & Related papers  (2025-01-09T03:59:10Z)
• From Silos to Systems: Process-Oriented Hazard Analysis for AI Systems [2.226040060318401]
  We translate System Theoretic Process Analysis (STPA) for analyzing AI operation and development processes. We focus on systems that rely on machine learning algorithms and conductedA on three case studies. We find that key concepts and steps of conducting anA readily apply, albeit with a few adaptations tailored for AI systems.
  arXiv  Detail & Related papers  (2024-10-29T20:43:18Z)
• Towards Guaranteed Safe AI: A Framework for Ensuring Robust and Reliable AI Systems [88.80306881112313]
  We will introduce and define a family of approaches to AI safety, which we will refer to as guaranteed safe (GS) AI. The core feature of these approaches is that they aim to produce AI systems which are equipped with high-assurance quantitative safety guarantees. We outline a number of approaches for creating each of these three core components, describe the main technical challenges, and suggest a number of potential solutions to them.
  arXiv  Detail & Related papers  (2024-05-10T17:38:32Z)
• ACCESS: Assurance Case Centric Engineering of Safety-critical Systems [9.388301205192082]
  Assurance cases are used to communicate and assess confidence in critical system properties such as safety and security. In recent years, model-based system assurance approaches have gained popularity to improve the efficiency and quality of system assurance activities. We show how model-based system assurance cases can trace to heterogeneous engineering artifacts.
  arXiv  Detail & Related papers  (2024-03-22T14:29:50Z)
• Safety Analysis of Autonomous Railway Systems: An Introduction to the SACRED Methodology [2.47737926497181]
  We introduce SACRED, a safety methodology for producing an initial safety case for autonomous systems. The development of SACRED is motivated by the proposed GoA-4 light-rail system in Berlin.
  arXiv  Detail & Related papers  (2024-03-18T11:12:19Z)
• Leveraging Traceability to Integrate Safety Analysis Artifacts into the Software Development Process [51.42800587382228]
  Safety assurance cases (SACs) can be challenging to maintain during system evolution. We propose a solution that leverages software traceability to connect relevant system artifacts to safety analysis models. We elicit design rationales for system changes to help safety stakeholders analyze the impact of system changes on safety.
  arXiv  Detail & Related papers  (2023-07-14T16:03:27Z)
• Towards Safer Generative Language Models: A Survey on Safety Risks, Evaluations, and Improvements [76.80453043969209]
  This survey presents a framework for safety research pertaining to large models. We begin by introducing safety issues of wide concern, then delve into safety evaluation methods for large models. We explore the strategies for enhancing large model safety from training to deployment.
  arXiv  Detail & Related papers  (2023-02-18T09:32:55Z)
• X-Risk Analysis for AI Research [24.78742908726579]
  We provide a guide for how to analyze AI x-risk. First, we review how systems can be made safer today. Next, we discuss strategies for having long-term impacts on the safety of future systems.
  arXiv  Detail & Related papers  (2022-06-13T00:22:50Z)
• Dos and Don'ts of Machine Learning in Computer Security [74.1816306998445]
  Despite great potential, machine learning in security is prone to subtle pitfalls that undermine its performance. We identify common pitfalls in the design, implementation, and evaluation of learning-based security systems. We propose actionable recommendations to support researchers in avoiding or mitigating the pitfalls where possible.
  arXiv  Detail & Related papers  (2020-10-19T13:09:31Z)
• 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.