{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T01:04:58Z","timestamp":1774400698288,"version":"3.50.1"},"reference-count":193,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"USA NSF","doi-asserted-by":"publisher","award":["CNS\/SaTC 2039583"],"award-info":[{"award-number":["CNS\/SaTC 2039583"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"USA NSF","doi-asserted-by":"publisher","award":["CNS 1650831"],"award-info":[{"award-number":["CNS 1650831"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"USA NSF","doi-asserted-by":"publisher","award":["1828811"],"award-info":[{"award-number":["1828811"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100012365","name":"DoD Center of Excellence in AI and Machine Learning at Howard University","doi-asserted-by":"publisher","award":["W911NF-20-2-0277"],"award-info":[{"award-number":["W911NF-20-2-0277"]}],"id":[{"id":"10.13039\/100012365","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006754","name":"USA Army Research Laboratory","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006754","id-type":"DOI","asserted-by":"publisher"}]},{"name":"USA Department of Homeland Security","award":["2017-ST-062-000003"],"award-info":[{"award-number":["2017-ST-062-000003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/comst.2020.3036778","type":"journal-article","created":{"date-parts":[[2020,11,9]],"date-time":"2020-11-09T21:19:43Z","timestamp":1604956783000},"page":"524-552","source":"Crossref","is-referenced-by-count":196,"title":["Resilient Machine Learning for Networked Cyber Physical Systems: A Survey for Machine Learning Security to Securing Machine Learning for CPS"],"prefix":"10.1109","volume":"23","author":[{"given":"Felix O.","family":"Olowononi","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3638-3464","authenticated-orcid":false,"given":"Danda B","family":"Rawat","sequence":"additional","affiliation":[]},{"given":"Chunmei","family":"Liu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref170","article-title":"Detecting adversarial examples by measuring their stress response","author":"sun","year":"2019"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30508-6_53"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00095"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.11.052"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.615"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2974509"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140444"},{"key":"ref178","first-page":"9916","article-title":"Online robust policy learning in the presence of unknown adversaries","author":"havens","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref177","author":"behzadan","year":"2017","journal-title":"Whatever does not kill deep reinforcement learning makes it stronger"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2019.05.084"},{"key":"ref169","author":"dathathri","year":"2018","journal-title":"Detecting adversarial examples via neural fingerprinting"},{"key":"ref39","author":"schulman","year":"2017","journal-title":"Proximal policy optimization algorithms"},{"key":"ref38","author":"lillicrap","year":"2015","journal-title":"Continuous control with deep reinforcement learning"},{"key":"ref33","author":"mnih","year":"2013","journal-title":"Playing atari with deep reinforcement learning"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2886017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2948912"},{"key":"ref37","first-page":"1889","article-title":"Trust region policy optimization","author":"schulman","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref35","first-page":"2154","article-title":"Value iteration networks","author":"tamar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref181","author":"weng","year":"2018","journal-title":"Towards Fast Computation of Certified Robustness for ReLU Networks"},{"key":"ref180","author":"lin","year":"2017","journal-title":"Detecting adversarial attacks on neural network policies with visual foresight"},{"key":"ref185","author":"raghunathan","year":"2018","journal-title":"Certified defenses against adversarial examples"},{"key":"ref184","author":"wang","year":"2019","journal-title":"Verification of neural network control policy under persistent adversarial perturbation"},{"key":"ref183","author":"everett","year":"2020","journal-title":"Certified adversarial robustness for deep reinforcement learning"},{"key":"ref182","author":"oikarinen","year":"2020","journal-title":"Robust deep reinforcement learning through adversarial loss"},{"key":"ref189","author":"qu","year":"2020","journal-title":"Defending adversarial attacks without adversarial attacks in deep reinforcement learning"},{"key":"ref188","author":"zhang","year":"2020","journal-title":"Robust deep reinforcement learning against adversarial perturbations on observations"},{"key":"ref187","author":"fischer","year":"2019","journal-title":"Online robustness training for deep reinforcement learning"},{"key":"ref186","first-page":"5286","article-title":"Provable defenses against adversarial examples via the convex outer adversarial polytope","author":"wong","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"crossref","first-page":"152","DOI":"10.1016\/j.procs.2018.10.315","article-title":"Adversarial attacks and defenses against deep neural networks: A survey","volume":"140","author":"ozdag","year":"2018","journal-title":"Procedia Comput Sci"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SSIRI-C.2011.15"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206245"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.07.023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10916-018-1045-z"},{"key":"ref22","author":"behzadan","year":"2018","journal-title":"Adversarial reinforcement learning framework for benchmarking collision avoidance mechanisms in autonomous vehicles"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3317572"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICRAS.2019.8808950"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2017.8324756"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/1128817.1128824"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/IVS.2018.8500675"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.23919\/JCC.2019.06.002"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICSECC.2019.8907054"},{"key":"ref154","author":"dhillon","year":"2018","journal-title":"Stochastic activation pruning for robust adversarial defense"},{"key":"ref153","first-page":"419","article-title":"Deep defense: Training dnns with improved adversarial robustness","author":"yan","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref156","author":"na","year":"2017","journal-title":"Cascade adversarial machine learning regularized with a unified embedding"},{"key":"ref155","author":"tram\u00e8r","year":"2017","journal-title":"Ensemble adversarial training Attacks and defenses"},{"key":"ref150","author":"metzen","year":"2017","journal-title":"On detecting adversarial perturbations"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.485"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00191"},{"key":"ref146","author":"guo","year":"2017","journal-title":"Countering adversarial images using input transformations"},{"key":"ref147","author":"xie","year":"2017","journal-title":"Mitigating adversarial effects through randomization"},{"key":"ref148","first-page":"1660","article-title":"Improving the adversarial robustness and interpretability of deep neural networks by regularizing their input gradients","author":"ross","year":"2018","journal-title":"Proc 32nd AAAI Conf Artif Intell"},{"key":"ref149","author":"srisakaokul","year":"2018","journal-title":"MULDEF Multi-model-based Defense Against Adversarial Examples for Neural Networks"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/MPE.2015.2397337"},{"key":"ref58","first-page":"6","article-title":"Take two software updates and see me in the morning: The case for software security evaluations of medical devices","author":"hanna","year":"2011","journal-title":"Proc 2nd USENIX Conf Health Security Privacy (HealthSec)"},{"key":"ref57","first-page":"129","article-title":"Pacemakers and implantable cardiac defibrillators: Software radio attacks and zero-power defenses","author":"halperin","year":"2008","journal-title":"Prof IEEE Symp Security and Privacy (SP)"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/1837274.1837463"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2963371"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1800510"},{"key":"ref53","author":"haghighi","year":"2020","journal-title":"A machine learning-based approach to build zero false-positive IPSS for industrial IoT and CPS with a case study on power grids security"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1117\/12.2519372"},{"key":"ref40","author":"jaderberg","year":"2016","journal-title":"Reinforcement learning with unsupervised auxiliary tasks"},{"key":"ref167","author":"roth","year":"2019","journal-title":"The odds are odd A statistical test for detecting adversarial examples"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.56"},{"key":"ref165","author":"feinman","year":"2017","journal-title":"Detecting adversarial samples from artifacts"},{"key":"ref164","author":"xu","year":"2017","journal-title":"Feature squeezing Detecting adversarial examples in deep neural networks"},{"key":"ref163","first-page":"284","article-title":"Synthesizing robust adversarial examples","author":"athalye","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref162","author":"athalye","year":"2018","journal-title":"Obfuscated gradients give a false sense of security Circumventing defenses to adversarial examples"},{"key":"ref161","author":"papernot","year":"2016","journal-title":"Towards the science of security and privacy in machine learning"},{"key":"ref160","author":"papernot","year":"2017","journal-title":"Extending defensive distillation"},{"key":"ref4","first-page":"10","article-title":"Internet of Things in healthcare","volume":"8","author":"ramachandran","year":"2019","journal-title":"Res Rev J Med Sci Technol"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICREST.2019.8644232"},{"key":"ref6","first-page":"3","article-title":"Industrial Internet of Things and cyber manufacturing systems","author":"jeschke","year":"2017","journal-title":"The Industrial Internet of Things"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD.2016.7566069"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TSUSC.2018.2809665"},{"key":"ref159","author":"papernot","year":"2016","journal-title":"On the effectiveness of defensive distillation"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2786546"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2018.2836144"},{"key":"ref157","first-page":"2654","article-title":"Do deep nets really need to be deep?","author":"ba","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1837274.1837461"},{"key":"ref158","author":"hinton","year":"2015","journal-title":"Distilling the knowledge in a neural network"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/s18114040"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2869399"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-44494-9_4"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.23919\/ACC.2019.8814721"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops49005.2020.9145335"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.arcontrol.2019.04.011"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MDAT.2017.2709310"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2017.2703172"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461233"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569635"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1800535"},{"key":"ref70","author":"makantasis","year":"2019","journal-title":"A deep reinforcement learning driving policy for autonomous road vehicles"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/MT-CPS.2018.00009"},{"key":"ref77","author":"kumar","year":"2019","journal-title":"Explainable AI Deep reinforcement learning agents for residential demand side cost savings in smart grids"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/WD.2019.8734192"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2018.2832219"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/89"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2941498"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3272036.3272037"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.02.020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2018.2890524"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s12530-020-09328-3"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/i-PACT44901.2019.8960090"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCP48234.2019.8959649"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2894819"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/JSYST.2014.2341597"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569568"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2018.8569316"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/IRI.2019.00039"},{"key":"ref95","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CGVIS.2015.7449922"},{"key":"ref190","author":"balaji","year":"2019","journal-title":"Instance adaptive adversarial training Improved accuracy tradeoffs in neural nets"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8285298"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2018.2869244"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/MED.2016.7535868"},{"key":"ref192","author":"zhao","year":"2018","journal-title":"Federated learning with non-IID data"},{"key":"ref91","author":"barbeau","year":"2019","journal-title":"Next generation resilient cyber-physical systems"},{"key":"ref90","first-page":"8g","article-title":"From dependability to resilience","author":"laprie","year":"2008","journal-title":"Proc 38th IEEE\/IFIP Int Conf Depend Syst Netw"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/GCWkshps45667.2019.9024550"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/ACC.2016.7524933"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-019-09717-4"},{"key":"ref97","author":"goodfellow","year":"2016","journal-title":"Nips 2016 tutorial Generative adversarial networks"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.6028\/NIST.GCR.16-010"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/PTC.2019.8810568"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TCNS.2016.2573039"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2019.2919635"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.apenergy.2019.04.119"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/524"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/2899015.2899016"},{"key":"ref86","first-page":"72","article-title":"Enhanced cyber-physical security through deep learning techniques","author":"macas","year":"2019","journal-title":"Proc CPS Summer School Ph D Workshop"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.25"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2017.8280915"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8714833"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1049\/iet-cta.2016.1226"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.282"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"ref125","author":"kurakin","year":"2016","journal-title":"Adversarial examples in the physical world"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00957"},{"key":"ref129","author":"carlini","year":"2016","journal-title":"Defensive distillation is not robust to adversarial examples"},{"key":"ref128","first-page":"2687","article-title":"Learning to attack: Adversarial transformation networks","author":"baluja","year":"2018","journal-title":"Proc AAAI"},{"key":"ref130","author":"ilahi","year":"2020","journal-title":"Challenges and countermeasures for adversarial attacks on deep reinforcement learning"},{"key":"ref133","author":"kos","year":"2017","journal-title":"Delving into adversarial attacks on deep policies"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/525"},{"key":"ref131","doi-asserted-by":"crossref","first-page":"262","DOI":"10.1007\/978-3-319-62416-7_19","article-title":"Vulnerability of deep reinforcement learning to policy induction attacks","author":"behzadan","year":"2017","journal-title":"Proc Int Conf Mach Learn Data Min Pattern Recognit"},{"key":"ref132","author":"huang","year":"2017","journal-title":"Adversarial attacks on neural network policies"},{"key":"ref136","author":"hussenot","year":"2019","journal-title":"Targeted attacks on deep reinforcement learning agents through adversarial observations"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6047"},{"key":"ref138","author":"lee","year":"2019","journal-title":"Spatiotemporally constrained action space attacks on deep reinforcement learning agents"},{"key":"ref137","author":"tretschk","year":"2018","journal-title":"Sequential attacks on agents for long-term adversarial goals"},{"key":"ref139","first-page":"16","article-title":"Blackbox attacks on reinforcement learning agents using approximated temporal information","author":"zhao","year":"2020","journal-title":"Proc 50th Annu IEEE\/IFIP Int Conf Depend Syst Netw Workshops (DSN-W)"},{"key":"ref140","author":"gleave","year":"2019","journal-title":"Adversarial policies Attacking deep reinforcement learning"},{"key":"ref141","author":"inkawhich","year":"2019","journal-title":"Snooping attacks on deep reinforcement learning"},{"key":"ref142","author":"pattanaik","year":"2017","journal-title":"Robust deep reinforcement learning with adversarial attacks"},{"key":"ref143","author":"chhabra","year":"2019","journal-title":"Strong black-box adversarial attacks on unsupervised machine learning models"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2942846"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5770"},{"key":"ref1","article-title":"The impact of broadband on the economy: Research and Policy issues","author":"katz","year":"2012","journal-title":"Proc Int Telecommun Union (ITU) Global Symp Regulators"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"ref109","author":"boursinos","year":"2020","journal-title":"Trusted confidence bounds for learning enabled cyber-physical systems"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/ICCPS48487.2020.00024"},{"key":"ref107","author":"cai","year":"2020","journal-title":"Detecting adversarial examples in learning-enabled cyber-physical systems using variational autoencoder for regression"},{"key":"ref106","author":"rosenberg","year":"2020","journal-title":"Adversarial learning in the cyber security domain"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2019.8715283"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/RUSAUTOCON.2018.8501783"},{"key":"ref103","first-page":"703","article-title":"MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks","author":"li","year":"2019","journal-title":"Proc Int Conf Artif Neural Netw"},{"key":"ref102","author":"li","year":"2018","journal-title":"Anomaly detection with generative adversarial networks for multivariate time series"},{"key":"ref111","author":"li","year":"2020","journal-title":"SearchFromFree Adversarial measurements for machine learning-based energy theft detection"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TrustCom\/BigDataSE.2018.00079"},{"key":"ref110","author":"boursinos","year":"2020","journal-title":"Assurance monitoring of cyber-physical systems with machine learning components"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2019.2961344"},{"key":"ref11","doi-asserted-by":"crossref","DOI":"10.1201\/9781351006620","author":"li","year":"2019","journal-title":"Reinforcement Learning for Cyber-Physical Systems with Cybersecurity Case Studies"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IECON.2018.8591773"},{"key":"ref13","author":"dartmann","year":"2019","journal-title":"Big Data Analytics for Cyber-Physical Systems Machine Learning for the Internet of Things"},{"key":"ref14","volume":"27","author":"ng","year":"2016","journal-title":"Why AI Is the New Electricity"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"239","DOI":"10.1007\/s12599-014-0334-4","article-title":"Industry 4.0","volume":"6","author":"lasi","year":"2014","journal-title":"Bus Inf Syst Eng"},{"key":"ref16","first-page":"2273","article-title":"Intelligent manufacturing-main direction of made in China 2025","volume":"26","author":"zhou","year":"2015","journal-title":"Chinese Journal of Mechanical Engineering"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3052973.3053009"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2825478"},{"key":"ref117","author":"chakraborty","year":"2018","journal-title":"Adversarial Attacks and Defences A Survey"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2017.08.043"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2018.00013"},{"key":"ref119","author":"liu","year":"2016","journal-title":"Delving into transferable adversarial examples and black-box attacks"},{"key":"ref114","author":"szegedy","year":"2013","journal-title":"Intriguing properties of neural networks"},{"key":"ref113","author":"xiong","year":"2020","journal-title":"Robustness to adversarial attacks in learning-enabled controllers"},{"key":"ref116","author":"goodfellow","year":"2014","journal-title":"Explaining and Harnessing Adversarial Examples"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/EuroSP.2016.36"},{"key":"ref120","author":"bhagoji","year":"2017","journal-title":"Exploring the Space of Black-box Attacks on Deep Neural Networks"},{"key":"ref121","author":"cheng","year":"2018","journal-title":"Query-Efficient Hard-label Black-box Attack An Optimization-based Approach"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1145\/3128572.3140448"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301742"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/9739\/9361471\/9252851-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9739\/9361471\/09252851.pdf?arnumber=9252851","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:52:26Z","timestamp":1652194346000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9252851\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":193,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/comst.2020.3036778","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}