Deployment of modern data-driven machine learning methods, most often realized by deep neural networks (DNNs), in safety-critical applications such as health care, industrial plant control, or autonomous driving is highly challenging due to numerous model-inherent shortcomings. These shortcomings are diverse and range from a lack of generalization over insufficient interpretability and implausible predictions to directed attacks by means of malicious inputs. Cyber-physical systems employing DNNs are therefore likely to suffer from so-called safety concerns, properties that preclude their deployment as no argument or experimental setup can help to assess the remaining risk. In recent years, an abundance of state-of-the-art techniques aiming to address these safety concerns has emerged. This chapter provides a structured and broad overview of them. We first identify categories of insufficiencies to then describe research activities aiming at their detection, quantification, or mitigation. Our work addresses machine learning experts and safety engineers alike: The former ones might profit from the broad range of machine learning topics covered and discussions on limitations of recent methods. The latter ones might gain insights into the specifics of modern machine learning methods. We hope that this contribution fuels discussions on desiderata for machine learning systems and strategies on how to help to advance existing approaches accordingly.


    Access

    Download


    Export, share and cite



    Title :

    Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety




    Publication date :

    2022-06-18


    Size :

    76 pages




    Type of media :

    Article/Chapter (Book)


    Type of material :

    Electronic Resource


    Language :

    English





    Robots to inspect welds underwater

    Kenzie, B. | Tema Archive | 1994


    Smart cameras inspect auto parts

    Wilson, A. | Tema Archive | 2003



    How to inspect a plane

    Marriott, J.S. | Engineering Index Backfile | 1932


    U.S. Railroaders inspect Japanese `super-railroad'

    Magee, G.M. | Engineering Index Backfile | 1963