arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2107.12045cs.LGcs.SE
收藏

如何认证基于机器学习的安全关键系统?一项系统性文献综述

How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review

Polytechnique Montréal(蒙特利尔综合理工学院);Laval University(拉瓦尔大学)

Florian Tambon, Gabriel Laberge, Le An, Amin Nikanjam, Paulina Stevia Nouwou Mindom, Yann Pequignot, Foutse Khomh, Giulio Antoniol, Ettore Merlo, François Laviolette

摘要:

背景:在过去的几年里,机器学习(ML)一直是许多创新的核心。然而,将其纳入所谓的“安全关键”系统(如汽车或航空)已被证明是非常具有挑战性的,因为ML带来的范式转变完全改变了传统的认证方法。目的:本文旨在阐明与基于ML的安全关键系统的认证相关的挑战,以及文献中提出的解决方案,以解决这些问题,回答“如何认证基于机器学习的安全关键系统?'.方法:我们对2015年至2020年期间发表的研究论文进行了系统性文献综述(SLR),涵盖与ML系统认证相关的主题。我们总共确定了217篇论文,涵盖了被认为是ML认证的主要支柱的主题:鲁棒性,不确定性,可解释性,验证,安全强化学习和直接认证。分析了各子领域的主要发展趋势和存在的问题,并对所抽取的论文进行了总结。结果如下:SLR结果突出了社区对这一主题的热情,以及数据集和模型类型缺乏多样性。它还强调需要进一步发展学术界和产业界之间的联系,以深化领域研究。最后,它还说明了在目前主要单独研究的上述主要支柱之间建立联系的必要性。结论:我们强调了当前为实现基于ML的软件系统认证所做的努力,并讨论了一些未来的研究方向。

英文摘要:

Context: Machine Learning (ML) has been at the heart of many innovations over the past years. However, including it in so-called 'safety-critical' systems such as automotive or aeronautic has proven to be very challenging, since the shift in paradigm that ML brings completely changes traditional certification approaches. Objective: This paper aims to elucidate challenges related to the certification of ML-based safety-critical systems, as well as the solutions that are proposed in the literature to tackle them, answering the question 'How to Certify Machine Learning Based Safety-critical Systems?'. Method: We conduct a Systematic Literature Review (SLR) of research papers published between 2015 to 2020, covering topics related to the certification of ML systems. In total, we identified 217 papers covering topics considered to be the main pillars of ML certification: Robustness, Uncertainty, Explainability, Verification, Safe Reinforcement Learning, and Direct Certification. We analyzed the main trends and problems of each sub-field and provided summaries of the papers extracted. Results: The SLR results highlighted the enthusiasm of the community for this subject, as well as the lack of diversity in terms of datasets and type of models. It also emphasized the need to further develop connections between academia and industries to deepen the domain study. Finally, it also illustrated the necessity to build connections between the above mention main pillars that are for now mainly studied separately. Conclusion: We highlighted current efforts deployed to enable the certification of ML based software systems, and discuss some future research directions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑