{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T13:35:13Z","timestamp":1762522513733,"version":"3.28.0"},"reference-count":56,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020,9,28]]},"DOI":"10.23919\/mipro48935.2020.9245153","type":"proceedings-article","created":{"date-parts":[[2020,11,6]],"date-time":"2020-11-06T21:51:34Z","timestamp":1604699494000},"page":"1254-1259","source":"Crossref","is-referenced-by-count":19,"title":["AI safety: state of the field through quantitative lens"],"prefix":"10.23919","author":[{"given":"Mislav","family":"Juric","sequence":"first","affiliation":[]},{"given":"Agneza","family":"Sandic","sequence":"additional","affiliation":[]},{"given":"Mario","family":"Brcic","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref39","article-title":"Fairness in Learning-Based Sequential Decision Algorithms: A Survey","author":"zhang","year":"2020","journal-title":"ArXiv200104861 Cs"},{"key":"ref38","article-title":"A Survey on Bias and Fairness in Machine Learning","author":"mehrabi","year":"2019","journal-title":"ArXiv190809635 Cs"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2807385"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-019-09408-y"},{"key":"ref31","first-page":"93:1","article-title":"A Survey of Methods for Explaining Black Box Models","volume":"51","author":"guidotti","year":"2018","journal-title":"ACM Comput Surv CSUR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1002\/isaf.1422"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2933524"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2019.03.003"},{"key":"ref34","article-title":"Adversarial Attacks and Defences: A Survey","author":"chakraborty","year":"2018","journal-title":"ArXiv181000069 Cs Stat"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2944672"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2870052"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2019.12.012"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/768"},{"journal-title":"Building safe artificial intelligence specification robustness and assurance","year":"2020","key":"ref1"},{"key":"ref20","first-page":"1","article-title":"Transparency and Algorithmic Governance","volume":"71","author":"coglianese","year":"2019","journal-title":"Adm Law Rev"},{"key":"ref22","article-title":"SMart Policies for Artificial Intelligence","author":"brundage","year":"2016","journal-title":"ArXiv160808196 Cs"},{"key":"ref21","first-page":"505","article-title":"Artificial Intelligence and the ‘Good Society’: the US, EU, and UK approach","volume":"24","author":"cath","year":"2018","journal-title":"Sci Eng Ethics"},{"key":"ref24","article-title":"AI Governance: A Research Agenda","author":"dafoe","year":"2018","journal-title":"Governance of AI Program Future of Humanity Institute University of Oxford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1098\/rsta.2018.0080"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.23919\/MIPRO.2018.8400040"},{"key":"ref25","article-title":"Unexplainability and Incomprehensibility of Artificial Intelligence","author":"yampolskiy","year":"2019","journal-title":"ArXiv190703869 Cs"},{"key":"ref50","article-title":"Supervising strong learners by amplifying weak experts","author":"christiano","year":"2018","journal-title":"ArXiv181008575 Cs Stat"},{"key":"ref51","article-title":"Scalable agent alignment via reward modeling: a research direction","author":"leike","year":"2018","journal-title":"ArXiv181107871 Cs Stat"},{"key":"ref56","article-title":"RELEVANCE OF ETHICAL GUIDELINES FOR ARTIFICIAL INTELLIGENCE – A SURVEY AND EVALUATION","author":"rothenberger","year":"2019","journal-title":"Res –Prog Pap"},{"key":"ref55","article-title":"Guidelines for Artificial Intelligence Containment","author":"babcock","year":"2017","journal-title":"ArXiv170708476 Cs"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-54033-6_5"},{"key":"ref53","article-title":"Risks from Learned Optimization in Advanced Machine Learning Systems","author":"hubinger","year":"2019","journal-title":"ArXiv190601820 Cs"},{"key":"ref52","article-title":"AI safety via debate","author":"irving","year":"2018","journal-title":"ArXiv180500899 Cs Stat"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1177\/2053951716679679"},{"key":"ref11","article-title":"Artificial Moral Agents: A Survey of the Current Status","author":"cervantes","year":"2019","journal-title":"Sci Eng Ethics"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1147\/JRD.2019.2915062"},{"key":"ref12","article-title":"Global AI Ethics: A Review of the Social Impacts and Ethical Implications of Artificial Intelligence","author":"hagerty","year":"2019","journal-title":"ArXiv190707892 Cs"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3267338"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0088-2"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.3486518"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1108\/JICES-04-2019-0039"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11948-019-00165-5"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2866769"},{"key":"ref19","first-page":"77","article-title":"Beyond MAD?: The race for artificial general intelligence","volume":"2018","author":"ramamoorthy","year":"2018","journal-title":"ITU J ICT Discoveries"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21552\/delphi\/2019\/4\/8"},{"key":"ref3","first-page":"217","article-title":"Safety Engineering for Artificial General Intelligence","volume":"32","author":"yampolskiy","year":"2013","journal-title":"Topoi"},{"key":"ref6","article-title":"Machine Learning Testing: Survey, Landscapes and Horizons","author":"zhang","year":"2019","journal-title":"ArXiv190610742 Cs Stat"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1088\/0031-8949\/90\/1\/018001"},{"key":"ref8","article-title":"Concrete Problems in AI Safety","author":"amodei","year":"2016","journal-title":"ArXiv160606565 Cs"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijinfomgt.2019.08.002"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1911517117"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v36i4.2577"},{"key":"ref46","article-title":"Corrigibility","author":"soares","year":"2015","journal-title":"Workshops at the Twenty-Ninth AAAI Conference on Artificial Intelligence"},{"key":"ref45","first-page":"1437","article-title":"A Comprehensive Survey on Safe Reinforcement Learning","volume":"16","author":"garc\u00eda","year":"2015","journal-title":"J Mach Learn Res"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-018-0637-6"},{"key":"ref47","article-title":"AI Safety Gridworlds","author":"leike","year":"2017","journal-title":"ArXiv171109883 Cs"},{"article-title":"Alignment for Advanced Machine Learning Systems","year":"2016","author":"taylor","key":"ref42"},{"key":"ref41","article-title":"Reinforcement Learning as a Framework for Ethical Decision Making","author":"abel","year":"2016","journal-title":"AAAI Workshop on AI Ethics and Society"},{"key":"ref44","article-title":"Learning from Learning Machines: Optimisation, Rules, and Social Norms","author":"lacroix","year":"2019","journal-title":"ArXiv200100006 Cs Stat"},{"key":"ref43","article-title":"Value Alignment or Misalignment - What Will Keep Systems Accountable?","author":"arnold","year":"2017","journal-title":"AAAI Workshop"}],"event":{"name":"2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO)","start":{"date-parts":[[2020,9,28]]},"location":"Opatija, Croatia","end":{"date-parts":[[2020,10,2]]}},"container-title":["2020 43rd International Convention on Information, Communication and Electronic Technology (MIPRO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9245088\/9245075\/09245153.pdf?arnumber=9245153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,13]],"date-time":"2021-01-13T05:09:53Z","timestamp":1610514593000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9245153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,28]]},"references-count":56,"URL":"https:\/\/doi.org\/10.23919\/mipro48935.2020.9245153","relation":{},"subject":[],"published":{"date-parts":[[2020,9,28]]}}}