{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:16:43Z","timestamp":1785604603919,"version":"3.56.0"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CNS-1936370 (SaTC CORE)"],"award-info":[{"award-number":["CNS-1936370 (SaTC CORE)"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","award":["DGE-1921485 (SFS)"],"award-info":[{"award-number":["DGE-1921485 (SFS)"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Dependable and Secure Comput."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tdsc.2024.3477272","type":"journal-article","created":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T17:58:42Z","timestamp":1728496722000},"page":"2086-2102","source":"Crossref","is-referenced-by-count":4,"title":["Learning Contextualized Action Representations in Sequential Decision Making for Adversarial Malware Optimization"],"prefix":"10.1109","volume":"22","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1367-3338","authenticated-orcid":false,"given":"Reza","family":"Ebrahimi","sequence":"first","affiliation":[{"name":"School of Information Systems and Management, University of South Florida, Tampa, FL, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1711-1041","authenticated-orcid":false,"given":"Jason","family":"Pacheco","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Arizona, Tucson, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"James","family":"Hu","sequence":"additional","affiliation":[{"name":"Artifical Intelligence Lab, University of Arizona, Tucson, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsinchun","family":"Chen","sequence":"additional","affiliation":[{"name":"Artifical Intelligence Lab, University of Arizona, Tucson, AZ, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The cost of malicious cyber activity to the U.S. economy","year":"2018"},{"key":"ref2","article-title":"Ninth annual cost of cybercrime study: Unlocking the value of improved cybersecurity protection","author":"Bissell","year":"2019"},{"key":"ref3","article-title":"Global ransomware damage costs","volume-title":"Cybercrime Mag.","author":"Morgan","year":"2019"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.cose.2017.09.001"},{"key":"ref5","article-title":"Learning to evade static PE machine learning malware models via reinforcement learning","author":"Anderson","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913439"},{"key":"ref7","article-title":"Non-negative networks against adversarial attacks","volume":"1050","author":"Fleshman","year":"2018","journal-title":"Stat"},{"key":"ref8","article-title":"Deep Convolutional Malware Classifiers Can Learn from Raw Executables and Lables","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kr\u010d\u00e1l"},{"key":"ref9","article-title":"Malware detection by eating a whole EXE","volume-title":"Proc. Workshops 32nd AAAI Conf. Artif. Intell.","author":"Raff","year":"2018"},{"key":"ref10","article-title":"Symantec unveils industry\u2019s first neural network to protect critical infrastructure from cyber warfare","year":"2018"},{"key":"ref11","article-title":"Automatic generation of adversarial examples for interpreting malware classifiers","author":"Song","year":"2020"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/INFOMAN.2019.8714698"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2021.3082330"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2908033"},{"key":"ref15","article-title":"Practical traffic-space adversarial attacks on learning-based NIDSs","author":"Han","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553214"},{"key":"ref17","article-title":"Optimization-guided binary diversification to mislead neural networks for malware detection","author":"Sharif","year":"2019"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SPW.2019.00015"},{"key":"ref19","article-title":"Creating adversarial malware examples using code insertion","author":"Park","year":"2019"},{"key":"ref20","article-title":"Towards deep learning models resistant to adversarial attacks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Madry"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3134599"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/SPW54247.2022.9833895"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/SaTML54575.2023.00031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SPW53761.2021.00021"},{"key":"ref25","first-page":"18872","article-title":"R-learning in actor-critic model offers a biologically relevant mechanism for sequential decision-making","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Shuvaev"},{"key":"ref26","author":"Sutton","year":"2018","journal-title":"Reinforcement Learning: An Introduction"},{"key":"ref27","first-page":"941","article-title":"Learning action representations for reinforcement learning","volume-title":"Proc. Mach. Learn. Res.","author":"Chandak"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929141"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/app9050909"},{"key":"ref30","article-title":"Binary black-box evasion attacks against deep learning-based static malware detectors with adversarial byte-level language model","volume-title":"Proc. AAAI Workshop Robust, Secure, Efficient Mach. Learn.","author":"Ebrahimi"},{"key":"ref31","article-title":"Burning the adversarial bridges: Robust windows malware detection against binary-level mutations","author":"Abusnaina","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3488932.3497768"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2021.3097296"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11416-023-00498-7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3374664.3375741"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3568562.3568636"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00470-5_23"},{"key":"ref38","first-page":"245","article-title":"Black-box attacks against RNN based malware detection algorithms","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Hu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.02.075"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-7561-3_11"},{"key":"ref41","article-title":"Algorithms for sequential decision making","author":"Littman","year":"1996"},{"key":"ref42","first-page":"7120","article-title":"VIREL: A variational inference framework for reinforcement learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fellows"},{"key":"ref43","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Fujimoto"},{"key":"ref44","first-page":"1856","article-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Haarnoja"},{"key":"ref45","article-title":"Sample efficient actor-critic with experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref46","article-title":"Learning to factor policies and action-value functions: Factored action space representations for deep reinforcement learning","author":"Sharma","year":"2017"},{"key":"ref47","article-title":"Deep reinforcement learning in large discrete action spaces","author":"Dulac-Arnold","year":"2016"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1523\/JNEUROSCI.0965-04.2004"},{"key":"ref49","article-title":"Neural probabilistic motor primitives for humanoid control","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Merel","year":"2018"},{"key":"ref50","first-page":"3566","article-title":"Learn what not to learn: Action elimination with deep reinforcement learning","volume-title":"Proc. Neural Inf. Process. Syst.","author":"Zahavy"},{"key":"ref51","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref52","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref53","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref54","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref55","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref56","article-title":"Language models are unsupervised multitask learners","author":"Radford","year":"2019"},{"key":"ref57","article-title":"EMBER: An open dataset for training static PE malware machine learning models","author":"Anderson","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/MALWARE.2015.7413680"},{"key":"ref59","first-page":"889","article-title":"Hierarchical neural story generation","volume-title":"Proc. 56th Annu. Meeting Assoc. Comput. Linguistics","author":"Fan"},{"key":"ref60","first-page":"1","article-title":"Learning from context: A multi-view deep learning architecture for malware detection","volume-title":"Proc. IEEE Secur. Privacy Workshop","author":"Kyadige"},{"key":"ref61","first-page":"729","article-title":"$\\lbrace${TESSERACT $\\rbrace$}: Eliminating experimental bias in malware classification across space and time","volume-title":"Proc. 28th {USENIX} Secur. Symp.","author":"Pendlebury"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-15618-7_5"},{"key":"ref63","article-title":"Malware evasion competition","author":"Anderson","year":"2019"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3133956.3133978"},{"key":"ref65","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.556"},{"key":"ref68","article-title":"Unsupervised prompt learning for vision-language models","author":"Huang","year":"2022"},{"key":"ref69","article-title":"Towards zero-label language learning","author":"Wang","year":"2021"},{"key":"ref70","article-title":"Extending defensive distillation","author":"Papernot","year":"2017"}],"container-title":["IEEE Transactions on Dependable and Secure Computing"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/8858\/10992672\/10711271-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8858\/10992672\/10711271.pdf?arnumber=10711271","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,15]],"date-time":"2025-05-15T19:37:31Z","timestamp":1747337851000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10711271\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":70,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tdsc.2024.3477272","relation":{},"ISSN":["1545-5971","1941-0018","2160-9209"],"issn-type":[{"value":"1545-5971","type":"print"},{"value":"1941-0018","type":"electronic"},{"value":"2160-9209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}