Richard Hawkins

Richard Hawkins, Chiara Picardi, Lucy Donnell et al.

Wildfires are a common problem in many areas of the world with often catastrophic consequences. A number of systems have been created to provide early warnings of wildfires, including those that use satellite data to detect fires. The increased availability of small satellites, such as CubeSats, allows the wildfire detection response time to be reduced by deploying constellations of multiple satellites over regions of interest. By using machine learned components on-board the satellites, constraints which limit the amount of data that can be processed and sent back to ground stations can be overcome. There are hazards associated with wildfire alert systems, such as failing to detect the presence of a wildfire, or detecting a wildfire in the incorrect location. It is therefore necessary to be able to create a safety assurance case for the wildfire alert ML component that demonstrates it is sufficiently safe for use. This paper describes in detail how a safety assurance case for an ML wildfire alert system is created. This represents the first fully developed safety case for an ML component containing explicit argument and evidence as to the safety of the machine learning.

Kester Clegg, Richard Hawkins, Ibrahim Habli et al.

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.

Calum Corrie Imrie, Ioannis Stefanakos, Sepeedeh Shahbeigi et al.

The rapid advancement of machine learning (ML) has led to its increasing integration into cyber-physical systems (CPS) across diverse domains. While CPS offer powerful capabilities, incorporating ML components introduces significant safety and assurance challenges. Among ML techniques, reinforcement learning (RL) is particularly suited for CPS due to its capacity to handle complex, dynamic environments where explicit models of interaction between system and environment are unavailable or difficult to construct. However, in safety-critical applications, this learning process must not only be effective but demonstrably safe. Safe-RL methods aim to address this by incorporating safety constraints during learning, yet they fall short in providing systematic assurance across the RL lifecycle. The AMLAS methodology offers structured guidance for assuring the safety of supervised learning components, but it does not directly apply to the unique challenges posed by RL. In this paper, we adapt AMLAS to provide a framework for generating assurance arguments for an RL-enabled system through an iterative process; AMLAS-RL. We demonstrate AMLAS-RL using a running example of a wheeled vehicle tasked with reaching a target goal without collision.

Ozan Vardal, Richard Hawkins, Colin Paterson et al.

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.

Lisa Jöckel, Michael Kläs, Janek Groß et al.

Assurance Cases (ACs) are an established approach in safety engineering to argue quality claims in a structured way. In the context of quality assurance for Machine Learning (ML)-based software components, ACs are also being discussed and appear promising. Tools for operationalizing ACs do exist, yet mainly focus on supporting safety engineers on the system level. However, assuring the quality of an ML component within the system is commonly the responsibility of data scientists, who are usually less familiar with these tools. To address this gap, we propose a framework to support the operationalization of ACs for ML components based on technologies that data scientists use on a daily basis: Python and Jupyter Notebook. Our aim is to make the process of creating ML-related evidence in ACs more effective. Results from the application of the framework, documented through notebooks, can be integrated into existing AC tools. We illustrate the application of the framework on an example excerpt concerned with the quality of the test data.

Erik Armengaud, Georg Macher, Alexander Massoner et al.

The open and cooperative nature of Cyber-Physical Systems (CPS) poses new challenges in assuring dependability. The DEIS project (Dependability Engineering Innovation for automotive CPS. This project has received funding from the European Union's Horizon 2020 research and innovation programme under grant agreement No 732242, see http://www.deis-project.eu) addresses these challenges by developing technologies that form a science of dependable system integration. In the core of these technologies lies the concept of a Digital Dependability Identity (DDI) of a component or system. DDIs are modular, composable, and executable in the field facilitating (a) efficient synthesis of component and system dependability information over the supply chain and (b) effective evaluation of this information in-the-field for safe and secure composition of highly distributed and autonomous CPS. The paper outlines the DDI concept and opportunities for application in four industrial use cases.

Richard Hawkins, Colin Paterson, Chiara Picardi et al.

Machine Learning (ML) is now used in a range of systems with results that are reported to exceed, under certain conditions, human performance. Many of these systems, in domains such as healthcare , automotive and manufacturing, exhibit high degrees of autonomy and are safety critical. Establishing justified confidence in ML forms a core part of the safety case for these systems. In this document we introduce a methodology for the Assurance of Machine Learning for use in Autonomous Systems (AMLAS). AMLAS comprises a set of safety case patterns and a process for (1) systematically integrating safety assurance into the development of ML components and (2) for generating the evidence base for explicitly justifying the acceptable safety of these components when integrated into autonomous system applications.

Ran Wei, Tim P. Kelly, Xiaotian Dai et al.

Assurance cases are used to demonstrate confidence in system properties of interest (e.g. safety and/or security). A number of system assurance approaches are adopted by industries in the safety-critical domain. However, the task of constructing assurance cases remains a manual, trivial and informal process. The Structured Assurance Case Metamodel (SACM) is a standard specified by the Object Management Group (OMG). SACM provides a richer set of features than existing system assurance languages/approaches. SACM provides a foundation for model-based system assurance, which has great potentials in growing technology domains such as Open Adaptive Systems. However, the intended usage of SACM has not been sufficiently explained. In addition, there has been no support to interoperate between existing assurance case (models) and SACM models. In this article, we explain the intended usage of SACM based on our involvement in the OMG specification process of SACM. In addition, to promote a model-based approach, we provide SACM compliant metamodels for existing system assurance approaches (the Goal Structuring Notation and Claims-Arguments-Evidence), and the transformations from these models to SACM. We also briefly discuss the tool support for model-based system assurance which helps practitioners to make the transition from existing system assurance approaches to model-based system assurance using SACM.