arXiv subjects

Ibrahim Habli

Publications and source records attributed to Ibrahim Habli.

At least 19 recordsLinked to original sources

arXiv2026

What Types of Human-AI Teams Exist?

Human-AI teaming has received increasing attention in the literature. However, the range of studies conducted in multiple domains make it difficult to understand what types of teams are being studied, and in what ways are they similar/different from one another. In this study, we analyse 53 papers on human-AI teams and categorise them into five main clusters based on psychological taxonomies of teaming; AI Assistant, Ad-hoc Dependency, Ad-hoc Forced Dependency, Paired Equanimity, and Group Equanimity. Each cluster represents a unique combination of holistic team-level characteristics, indicating there are multiple disparate team types studied under the same definition. In turn, this raises the question of whether insights are truly transferable between papers. We conclude with guidance on how to identify the types of human-AI teams studied, a checklist for reporting a human-AI team in research work, and ways in which the field can be further synthesised.

cs.HC↗

arXiv2026

I'm Sorry Driver, I'm Afraid I Can't Do That: Appraising the Safety of LLMs within Automotive Contexts

This paper appraises recent frameworks within AI development to integrate LLMs into control tasks in automotive contexts from the perspective of safety assurance. This work has built upon the rapid integration of LLMs across automotive settings. However, we find that at present, these frameworks face significant challenges, limiting their efficacy in real-time safety-critical contexts. Firstly, we consider conceptual challenges, including the fact that deployers are faced with a dual challenge, wherein they must assure a model which has been developed upstream, i.e. as general-purpose tools by the large AI labs, in a downstream context, i.e. into specific vehicle architectures. Secondly, we consider concrete challenges from across existing standards. We show that there are currently both fundamental engineering constraints covered in ISO21448, such as latency, and novel LLM-specific issues, such as alignment-related issues covered in ISO/PAS8800. We ground both examples in a concrete introductory, experimental case study exploring an existing open-source repository, Talk2Drive. We present a safety argument in order to make explicit the limitations of existing solutions. Nonetheless, given that the use of LLMs in automotive contexts is being explored at a technical level and operationalised, we propose potential assurance mechanisms for LLM-related hazardous events going forward.

cs.SE↗

arXiv2026

Clear, Compelling Arguments: Rethinking the Foundations of Frontier AI Safety Cases

This paper contributes to the nascent debate around safety cases for frontier AI systems. Safety cases are structured, defensible arguments that a system is acceptably safe to deploy in a given context. Historically, they have been used in safety-critical industries, such as aerospace, nuclear or automotive. As a result, safety cases for frontier AI have risen in prominence, both in the safety policies of leading frontier developers and in international research agendas proposed by leaders in generative AI, such as the Singapore Consensus on Global AI Safety Research Priorities and the International AI Safety Report. This paper appraises this work. We note that research conducted within the alignment community which draws explicitly on lessons from the assurance community has significant limitations. We therefore aim to rethink existing approaches to alignment safety cases. We offer lessons from existing methodologies within safety assurance and outline the limitations involved in the alignment community's current approach. Building on this foundation, we present a case study for a safety case focused on Deceptive Alignment and CBRN capabilities, drawing on existing, theoretical safety case "sketches" created by the alignment safety case community. Overall, we contribute holistic insights from the field of safety assurance via rigorous theory and methodologies that have been applied in safety-critical contexts. We do so in order to create a better foundational framework for robust, defensible and useful safety case methodologies which can help to assure the safety of frontier AI systems.

cs.CY↗

arXiv2026

A Calibrated Memorization Index (MI) for Detecting Training Data Leakage in Generative MRI Models

Image generative models are known to duplicate images from the training data as part of their outputs, which can lead to privacy concerns when used for medical image generation. We propose a calibrated per-sample metric for detecting memorization and duplication of training data. Our metric uses image features extracted using an MRI foundation model, aggregates multi-layer whitened nearest-neighbor similarities, and maps them to a bounded \emph{Overfit/Novelty Index} (ONI) and \emph{Memorization Index} (MI) scores. Across three MRI datasets with controlled duplication percentages and typical image augmentations, our metric robustly detects duplication and provides more consistent metric values across datasets. At the sample level, our metric achieves near-perfect detection of duplicates.

cs.CV↗

arXiv2026

Formal Evidence Generation for Assurance Cases for Robotic Software Models

Robotics and Autonomous Systems are increasingly deployed in safety-critical domains, so that demonstrating their safety is essential. Assurance Cases (ACs) provide structured arguments supported by evidence, but generating and maintaining this evidence is labour-intensive, error-prone, and difficult to keep consistent as systems evolve. We present a model-based approach to systematically generating AC evidence by embedding formal verification into the assurance workflow. The approach addresses three challenges: systematically deriving formal assertions from natural language requirements using templates, orchestrating multiple formal verification tools to handle diverse property types, and integrating formal evidence production into the workflow. Leveraging RoboChart, a domain-specific modelling language with formal semantics, we combine model checking and theorem proving in our approach. Structured requirements are automatically transformed into formal assertions using predefined templates, and verification results are automatically integrated as evidence. Case studies demonstrate the effectiveness of our approach.

cs.SE↗

arXiv2025

Evaluating Metrics for Safety with LLM-as-Judges

LLMs (Large Language Models) are increasingly used in text processing pipelines to intelligently respond to a variety of inputs and generation tasks. This raises the possibility of replacing human roles that bottleneck existing information flows, either due to insufficient staff or process complexity. However, LLMs make mistakes and some processing roles are safety critical. For example, triaging post-operative care to patients based on hospital referral letters, or updating site access schedules in nuclear facilities for work crews. If we want to introduce LLMs into critical information flows that were previously performed by humans, how can we make them safe and reliable? Rather than make performative claims about augmented generation frameworks or graph-based techniques, this paper argues that the safety argument should focus on the type of evidence we get from evaluation points in LLM processes, particularly in frameworks that employ LLM-as-Judges (LaJ) evaluators. This paper argues that although we cannot get deterministic evaluations from many natural language processing tasks, by adopting a basket of weighted metrics it may be possible to lower the risk of errors within an evaluation, use context sensitivity to define error severity and design confidence thresholds that trigger human review of critical LaJ judgments when concordance across evaluators is low.

cs.CL↗

arXiv2025

WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue

As Automatic Speech Recognition (ASR) is increasingly deployed in clinical dialogue, standard evaluations still rely heavily on Word Error Rate (WER). This paper challenges that standard, investigating whether WER or other common metrics correlate with the clinical impact of transcription errors. We establish a gold-standard benchmark by having expert clinicians compare ground-truth utterances to their ASR-generated counterparts, labeling the clinical impact of any discrepancies found in two distinct doctor-patient dialogue datasets. Our analysis reveals that WER and a comprehensive suite of existing metrics correlate poorly with the clinician-assigned risk labels (No, Minimal, or Significant Impact). To bridge this evaluation gap, we introduce an LLM-as-a-Judge, programmatically optimized using GEPA through DSPy to replicate expert clinical assessment. The optimized judge (Gemini-2.5-Pro) achieves human-comparable performance, obtaining 90% accuracy and a strong Cohen's kappa of 0.816. This work provides a validated, automated framework for moving ASR evaluation beyond simple textual fidelity to a necessary, scalable assessment of safety in clinical dialogue.

cs.CL↗

arXiv2025

Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems

The operational capabilities and application domains of AI-enabled autonomous systems have expanded significantly in recent years due to advances in robotics and machine learning (ML). Demonstrating the safety of autonomous systems rigorously is critical for their responsible adoption but it is challenging as it requires robust methodologies that can handle novel and uncertain situations throughout the system lifecycle, including detecting out-of-distribution (OoD) data. Thus, OOD detection is receiving increased attention from the research, development and safety engineering communities. This comprehensive review analyses OOD detection techniques within the context of safety assurance for autonomous systems, in particular in safety-critical domains. We begin by defining the relevant concepts, investigating what causes OOD and exploring the factors which make the safety assurance of autonomous systems and OOD detection challenging. Our review identifies a range of techniques which can be used throughout the ML development lifecycle and we suggest areas within the lifecycle in which they may be used to support safety assurance arguments. We discuss a number of caveats that system and safety engineers must be aware of when integrating OOD detection into system lifecycles. We conclude by outlining the challenges and future work necessary for the safe development and operation of autonomous systems across a range of domains and applications.

cs.AI↗

arXiv2025

MATRIX: Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation

Despite the growing use of large language models (LLMs) in clinical dialogue systems, existing evaluations focus on task completion or fluency, offering little insight into the behavioral and risk management requirements essential for safety-critical systems. This paper presents MATRIX (Multi-Agent simulaTion fRamework for safe Interactions and conteXtual clinical conversational evaluation), a structured, extensible framework for safety-oriented evaluation of clinical dialogue agents. MATRIX integrates three components: (1) a safety-aligned taxonomy of clinical scenarios, expected system behaviors and failure modes derived through structured safety engineering methods; (2) BehvJudge, an LLM-based evaluator for detecting safety-relevant dialogue failures, validated against expert clinician annotations; and (3) PatBot, a simulated patient agent capable of producing diverse, scenario-conditioned responses, evaluated for realism and behavioral fidelity with human factors expertise, and a patient-preference study. Across three experiments, we show that MATRIX enables systematic, scalable safety evaluation. BehvJudge with Gemini 2.5-Pro achieves expert-level hazard detection (F1 0.96, sensitivity 0.999), outperforming clinicians in a blinded assessment of 240 dialogues. We also conducted one of the first realism analyses of LLM-based patient simulation, showing that PatBot reliably simulates realistic patient behavior in quantitative and qualitative evaluations. Using MATRIX, we demonstrate its effectiveness in benchmarking five LLM agents across 2,100 simulated dialogues spanning 14 hazard scenarios and 10 clinical domains. MATRIX is the first framework to unify structured safety engineering with scalable, validated conversational AI evaluation, enabling regulator-aligned safety auditing. We release all evaluation tools, prompts, structured scenarios, and datasets.

cs.AI↗

arXiv2025

Metrics that matter: Evaluating image quality metrics for medical image generation

Evaluating generative models for synthetic medical imaging is crucial yet challenging, especially given the high standards of fidelity, anatomical accuracy, and safety required for clinical applications. Standard evaluation of generated images often relies on no-reference image quality metrics when ground truth images are unavailable, but their reliability in this complex domain is not well established. This study comprehensively assesses commonly used no-reference image quality metrics using brain MRI data, including tumour and vascular images, providing a representative exemplar for the field. We systematically evaluate metric sensitivity to a range of challenges, including noise, distribution shifts, and, critically, localised morphological alterations designed to mimic clinically relevant inaccuracies. We then compare these metric scores against model performance on a relevant downstream segmentation task, analysing results across both controlled image perturbations and outputs from different generative model architectures. Our findings reveal significant limitations: many widely-used no-reference image quality metrics correlate poorly with downstream task suitability and exhibit a profound insensitivity to localised anatomical details crucial for clinical validity. Furthermore, these metrics can yield misleading scores regarding distribution shifts, e.g. data memorisation. This reveals the risk of misjudging model readiness, potentially leading to the deployment of flawed tools that could compromise patient safety. We conclude that ensuring generative models are truly fit for clinical purpose requires a multifaceted validation framework, integrating performance on relevant downstream tasks with the cautious interpretation of carefully selected no-reference image quality metrics.

eess.IV↗

arXiv2025

The case for delegated AI autonomy for Human AI teaming in healthcare

In this paper we propose an advanced approach to integrating artificial intelligence (AI) into healthcare: autonomous decision support. This approach allows the AI algorithm to act autonomously for a subset of patient cases whilst serving a supportive role in other subsets of patient cases based on defined delegation criteria. By leveraging the complementary strengths of both humans and AI, it aims to deliver greater overall performance than existing human-AI teaming models. It ensures safe handling of patient cases and potentially reduces clinician review time, whilst being mindful of AI tool limitations. After setting the approach within the context of current human-AI teaming models, we outline the delegation criteria and apply them to a specific AI-based tool used in histopathology. The potential impact of the approach and the regulatory requirements for its successful implementation are then discussed.

cs.AI↗

arXiv2025

The BIG Argument for AI Safety Cases

We present our Balanced, Integrated and Grounded (BIG) argument for assuring the safety of AI systems. The BIG argument adopts a whole-system approach to constructing a safety case for AI systems of varying capability, autonomy and criticality. Firstly, it is balanced by addressing safety alongside other critical ethical issues such as privacy and equity, acknowledging complexities and trade-offs in the broader societal impact of AI. Secondly, it is integrated by bringing together the social, ethical and technical aspects of safety assurance in a way that is traceable and accountable. Thirdly, it is grounded in long-established safety norms and practices, such as being sensitive to context and maintaining risk proportionality. Whether the AI capability is narrow and constrained or general-purpose and powered by a frontier or foundational model, the BIG argument insists on a systematic treatment of safety. Further, it places a particular focus on the novel hazardous behaviours emerging from the advanced capabilities of frontier AI models and the open contexts in which they are rapidly being deployed. These complex issues are considered within a wider AI safety case, approaching assurance from both technical and sociotechnical perspectives. Examples illustrating the use of the BIG argument are provided throughout the paper.

cs.CY↗

arXiv2024

Upstream and Downstream AI Safety: Both on the Same River?

Traditional safety engineering assesses systems in their context of use, e.g. the operational design domain (road layout, speed limits, weather, etc.) for self-driving vehicles (including those using AI). We refer to this as downstream safety. In contrast, work on safety of frontier AI, e.g. large language models which can be further trained for downstream tasks, typically considers factors that are beyond specific application contexts, such as the ability of the model to evade human control, or to produce harmful content, e.g. how to make bombs. We refer to this as upstream safety. We outline the characteristics of both upstream and downstream safety frameworks then explore the extent to which the broad AI safety community can benefit from synergies between these frameworks. For example, can concepts such as common mode failures from downstream safety be used to help assess the strength of AI guardrails? Further, can the understanding of the capabilities and limitations of frontier AI be used to inform downstream safety analysis, e.g. where LLMs are fine-tuned to calculate voyage plans for autonomous vessels? The paper identifies some promising avenues to explore and outlines some challenges in achieving synergy, or a confluence, between upstream and downstream safety frameworks.

cs.CY↗

arXiv2024

Learning Run-time Safety Monitors for Machine Learning Components

For machine learning components used as part of autonomous systems (AS) in carrying out critical tasks it is crucial that assurance of the models can be maintained in the face of post-deployment changes (such as changes in the operating environment of the system). A critical part of this is to be able to monitor when the performance of the model at runtime (as a result of changes) poses a safety risk to the system. This is a particularly difficult challenge when ground truth is unavailable at runtime. In this paper we introduce a process for creating safety monitors for ML components through the use of degraded datasets and machine learning. The safety monitor that is created is deployed to the AS in parallel to the ML component to provide a prediction of the safety risk associated with the model output. We demonstrate the viability of our approach through some initial experiments using publicly available speed sign datasets.

cs.LG↗

arXiv2024

Fair by design: A sociotechnical approach to justifying the fairness of AI-enabled systems across the lifecycle

Fairness is one of the most commonly identified ethical principles in existing AI guidelines, and the development of fair AI-enabled systems is required by new and emerging AI regulation. But most approaches to addressing the fairness of AI-enabled systems are limited in scope in two significant ways: their substantive content focuses on statistical measures of fairness, and they do not emphasize the need to identify and address fairness considerations across the whole AI lifecycle. Our contribution is to present an assurance framework and tool that can enable a practical and transparent method for widening the scope of fairness considerations across the AI lifecycle and move the discussion beyond mere statistical notions of fairness to consider a richer analysis in a practical and context-dependent manner. To illustrate this approach, we first describe and then apply the framework of Trustworthy and Ethical Assurance (TEA) to an AI-enabled clinical diagnostic support system (CDSS) whose purpose is to help clinicians predict the risk of developing hypertension in patients with Type 2 diabetes, a context in which several fairness considerations arise (e.g., discrimination against patient subgroups). This is supplemented by an open-source tool and a fairness considerations map to help facilitate reasoning about the fairness of AI-enabled systems in a participatory way. In short, by using a shared framework for identifying, documenting and justifying fairness considerations, and then using this deliberative exercise to structure an assurance case, research on AI fairness becomes reusable and generalizable for others in the ethical AI community and for sharing best practices for achieving fairness and equity in digital health and healthcare in particular.

cs.CY↗

arXiv2024

ACCESS: Assurance Case Centric Engineering of Safety-critical Systems

Assurance cases are used to communicate and assess confidence in critical system properties such as safety and security. Historically, assurance cases have been manually created documents, which are evaluated by system stakeholders through lengthy and complicated processes. In recent years, model-based system assurance approaches have gained popularity to improve the efficiency and quality of system assurance activities. This becomes increasingly important, as systems becomes more complex, it is a challenge to manage their development life-cycles, including coordination of development, verification and validation activities, and change impact analysis in inter-connected system assurance artifacts. Moreover, there is a need for assurance cases that support evolution during the operational life of the system, to enable continuous assurance in the face of an uncertain environment, as Robotics and Autonomous Systems (RAS) are adopted into society. In this paper, we contribute ACCESS - Assurance Case Centric Engineering of Safety-critical Systems, an engineering methodology, together with its tool support, for the development of safety critical systems around evolving model-based assurance cases. We show how model-based system assurance cases can trace to heterogeneous engineering artifacts (e.g. system architectural models, system safety analysis, system behaviour models, etc.), and how formal methods can be integrated during the development process. We demonstrate how assurance cases can be automatically evaluated both at development and runtime. We apply our approach to a case study based on an Autonomous Underwater Vehicle (AUV).

cs.SE↗

arXiv2023

What's my role? Modelling responsibility for AI-based safety-critical systems

AI-Based Safety-Critical Systems (AI-SCS) are being increasingly deployed in the real world. These can pose a risk of harm to people and the environment. Reducing that risk is an overarching priority during development and operation. As more AI-SCS become autonomous, a layer of risk management via human intervention has been removed. Following an accident it will be important to identify causal contributions and the different responsible actors behind those to learn from mistakes and prevent similar future events. Many authors have commented on the "responsibility gap" where it is difficult for developers and manufacturers to be held responsible for harmful behaviour of an AI-SCS. This is due to the complex development cycle for AI, uncertainty in AI performance, and dynamic operating environment. A human operator can become a "liability sink" absorbing blame for the consequences of AI-SCS outputs they weren't responsible for creating, and may not have understanding of. This cross-disciplinary paper considers different senses of responsibility (role, moral, legal and causal), and how they apply in the context of AI-SCS safety. We use a core concept (Actor(A) is responsible for Occurrence(O)) to create role responsibility models, producing a practical method to capture responsibility relationships and provide clarity on the previously identified responsibility issues. Our paper demonstrates the approach with two examples: a retrospective analysis of the Tempe Arizona fatal collision involving an autonomous vehicle, and a safety focused predictive role-responsibility analysis for an AI-based diabetes co-morbidity predictor. In both examples our primary focus is on safety, aiming to reduce unfair or disproportionate blame being placed on operators or developers. We present a discussion and avenues for future research.

cs.CY↗

arXiv2023

Unravelling Responsibility for AI

It is widely acknowledged that we need to establish where responsibility lies for the outputs and impacts of AI-enabled systems. This is important to achieve justice and compensation for victims of AI harms, and to inform policy and engineering practice. But without a clear, thorough understanding of what "responsibility" means, deliberations about where responsibility lies will be, at best, unfocused and incomplete and, at worst, misguided. Furthermore, AI-enabled systems exist within a wider ecosystem of actors, decisions, and governance structures, giving rise to complex networks of responsibility relations. To address these issues, this paper presents a conceptual framework of responsibility, accompanied with a graphical notation and general methodology for visualising these responsibility networks and for tracing different responsibility attributions for AI. Taking the three-part formulation "Actor A is responsible for Occurrence O," the framework unravels the concept of responsibility to clarify that there are different possibilities of who is responsible for AI, senses in which they are responsible, and aspects of events they are responsible for. The notation allows these permutations to be represented graphically. The methodology enables users to apply the framework to specific scenarios. The aim is to offer a foundation to support stakeholders from diverse disciplinary backgrounds to discuss and address complex responsibility questions in hypothesised and real-world cases involving AI. The work is illustrated by application to a fictitious scenario of a fatal collision between a crewless, AI-enabled maritime vessel in autonomous mode and a traditional, crewed vessel at sea.

cs.AI↗