{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T05:57:08Z","timestamp":1777874228907,"version":"3.51.4"},"reference-count":150,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T00:00:00Z","timestamp":1782864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,7]]},"DOI":"10.1016\/j.neucom.2026.133503","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T17:33:03Z","timestamp":1775755983000},"page":"133503","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Enhancing security in deep reinforcement learning: A comprehensive survey on adversarial attacks and defenses"],"prefix":"10.1016","volume":"685","author":[{"given":"Yichao","family":"Wu","sequence":"first","affiliation":[]},{"given":"Yirui","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Hailong","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Bingqian","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Panpan","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Chun","family":"Liu","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.133503_bib1","first-page":"1","article-title":"Smart city electricity load forecasting using greylag goose optimization-enhanced time series analysis","author":"El-Kenawy","year":"2025","journal-title":"Arab. J. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.133503_bib2","article-title":"Deep reinforcement learning for decision-making and control of autonomous driving: A survey","author":"Luo","year":"2025","journal-title":"Inf. Control"},{"issue":"5","key":"10.1016\/j.neucom.2026.133503_bib3","first-page":"677","article-title":"An overview of large model-driven embodied intelligent navigation","volume":"59","author":"Xie","year":"2025","journal-title":"J. Cent. China Norm. Univ. Nat. Sci."},{"issue":"6","key":"10.1016\/j.neucom.2026.133503_bib4","first-page":"1201","article-title":"A survey of task-oriented dialogue policies based on reinforcement learning","volume":"47","author":"Xu","year":"2024","journal-title":"Chin. J. Comput."},{"issue":"2","key":"10.1016\/j.neucom.2026.133503_bib5","doi-asserted-by":"crossref","DOI":"10.1371\/journal.pone.0278491","article-title":"Feature selection in wind speed forecasting systems based on meta-heuristic optimization","volume":"18","author":"El-Kenawy","year":"2023","journal-title":"Plos One"},{"key":"10.1016\/j.neucom.2026.133503_bib6","first-page":"1465","article-title":"Dipper throated optimization algorithm for unconstrained function and feature selection","volume":"72","author":"Takieldeen","year":"2022","journal-title":"Comput. Mater. Contin."},{"issue":"7587","key":"10.1016\/j.neucom.2026.133503_bib7","doi-asserted-by":"crossref","first-page":"484","DOI":"10.1038\/nature16961","article-title":"Mastering the game of Go with deep neural networks and tree search","volume":"529","author":"Silver","year":"2016","journal-title":"nature"},{"key":"10.1016\/j.neucom.2026.133503_bib8","article-title":"Mastering chess and shogi by self-play with a general reinforcement learning algorithm","author":"Silver","year":"2017","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib9","article-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019","journal-title":"arXiv Prepr."},{"issue":"7782","key":"10.1016\/j.neucom.2026.133503_bib10","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"Vinyals","year":"2019","journal-title":"nature"},{"key":"10.1016\/j.neucom.2026.133503_bib11","article-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017","journal-title":"arXiv Prepr"},{"key":"10.1016\/j.neucom.2026.133503_bib12","doi-asserted-by":"crossref","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network","volume":"404","author":"Sherstinsky","year":"2020","journal-title":"Physica D Nonlinear Phenomena"},{"issue":"6","key":"10.1016\/j.neucom.2026.133503_bib13","doi-asserted-by":"crossref","first-page":"4909","DOI":"10.1109\/TITS.2021.3054625","article-title":"Deep reinforcement learning for autonomous driving: a survey","volume":"23","author":"Kiran","year":"2021","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"5","key":"10.1016\/j.neucom.2026.133503_bib14","doi-asserted-by":"crossref","first-page":"674","DOI":"10.26599\/TST.2021.9010012","article-title":"Deep reinforcement learning based mobile robot navigation: a review","volume":"26","author":"Zhu","year":"2021","journal-title":"Tsinghua Sci. Technol."},{"issue":"8","key":"10.1016\/j.neucom.2026.133503_bib15","first-page":"1","article-title":"Overview on multi-agent reinforcement learning","volume":"46","author":"Du","year":"2019","journal-title":"Comput. Sci."},{"key":"10.1016\/j.neucom.2026.133503_bib16","article-title":"Secure and imperceptible medical image watermarking via multiscale QR embedding and attention-based optimization","volume":"73","author":"Beggari","year":"2026","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"10.1016\/j.neucom.2026.133503_bib17","article-title":"Hybrid fragile image watermarking for tamper detection, localization and dual self-recovery","volume":"73","author":"Sahu","year":"2026","journal-title":"Eng. Sci. Technol. Int. J."},{"key":"10.1016\/j.neucom.2026.133503_bib18","doi-asserted-by":"crossref","first-page":"94227","DOI":"10.1109\/ACCESS.2023.3312022","article-title":"A binary waterwheel plant optimization algorithm for feature selection","volume":"11","author":"Alhussan","year":"2023","journal-title":"IEEE Access"},{"issue":"4","key":"10.1016\/j.neucom.2026.133503_bib19","first-page":"1","article-title":"Robust rgb-t tracking via adaptive modality weight correlation filters and cross-modality learning","volume":"20","author":"Zhou","year":"2023","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.neucom.2026.133503_bib20","article-title":"AFES: attention-based feature excitation and sorting for action recognition","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Consum. Electron."},{"issue":"2","key":"10.1016\/j.neucom.2026.133503_bib21","doi-asserted-by":"crossref","first-page":"369","DOI":"10.1109\/TBC.2022.3215249","article-title":"An end-to-end blind image quality assessment method using a recurrent network and self-attention","volume":"69","author":"Zhou","year":"2022","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.neucom.2026.133503_bib22","first-page":"1","article-title":"Boundary-aware feature fusion with dual-stream attention for remote sensing small object detection","volume":"63","author":"Song","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.133503_bib23","article-title":"A critical review of safe reinforcement learning techniques in smart grid applications","author":"Bui","year":"2024","journal-title":"arXiv Prepr"},{"key":"10.1016\/j.neucom.2026.133503_bib24","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102303","article-title":"Adversarial attacks and defenses in explainable artificial intelligence: a survey","author":"Baniecki","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.133503_bib25","article-title":"Safe and robust reinforcement learning: Principles and practice","author":"Yamagata","year":"2024","journal-title":"arXiv Prepr"},{"issue":"8","key":"10.1016\/j.neucom.2026.133503_bib26","first-page":"1553","article-title":"A survey on adversarial attacks and defenses for deep reinforcement","volume":"46","author":"Liu","year":"2023","journal-title":"Chin. J. Comput."},{"key":"10.1016\/j.neucom.2026.133503_bib27","article-title":"COFNet: contrastive object-aware fusion using box-level masks for multispectral object detection","author":"Zhou","year":"2025","journal-title":"IEEE Trans. Multimed."},{"issue":"11","key":"10.1016\/j.neucom.2026.133503_bib28","doi-asserted-by":"crossref","first-page":"12994","DOI":"10.1109\/TII.2024.3431044","article-title":"Ef-detr: a lightweight transformer-based object detector with an encoder-free neck","volume":"20","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.neucom.2026.133503_bib29","doi-asserted-by":"crossref","DOI":"10.1109\/TII.2025.3588622","article-title":"GAANet: graph aggregation alignment feature fusion for multispectral object detection","author":"Zheng","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"issue":"6","key":"10.1016\/j.neucom.2026.133503_bib30","doi-asserted-by":"crossref","first-page":"3242","DOI":"10.1007\/s11263-024-02338-7","article-title":"Blind image quality assessment: exploring content fidelity perceptibility via quality adversarial learning","volume":"133","author":"Zhou","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.133503_bib31","doi-asserted-by":"crossref","DOI":"10.1109\/TCSVT.2025.3586106","article-title":"No-reference image quality assessment: exploring intrinsic distortion characteristics via generative noise estimation with mamba","author":"Lan","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.neucom.2026.133503_bib32","series-title":"Proceedings of the Proceedings of the Computer Vision and Pattern Recognition Conference, F","article-title":"Image quality assessment: Investigating causal perceptual effects with abductive counterfactual inference","author":"Shen","year":"2025"},{"key":"10.1016\/j.neucom.2026.133503_bib33","article-title":"Explaining and harnessing adversarial examples","author":"Goodfellow","year":"2014","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib34","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","author":"Hendrycks","year":"2016","journal-title":"arXiv Prepr"},{"key":"10.1016\/j.neucom.2026.133503_bib35","series-title":"Proceedings of the Proceedings of the 2017 Acm on Asia Conference on Computer and Communications Security, F","article-title":"Practical black-box attacks against machine learning","author":"Papernot","year":"2017"},{"key":"10.1016\/j.neucom.2026.133503_bib36","doi-asserted-by":"crossref","first-page":"12103","DOI":"10.1109\/ACCESS.2018.2805680","article-title":"A survey on security threats and defensive techniques of machine learning: a data driven view","volume":"6","author":"Liu","year":"2018","journal-title":"IEEE Access"},{"issue":"1","key":"10.1016\/j.neucom.2026.133503_bib37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3691625","article-title":"Adversarial attacks and countermeasures on image classification-based deep learning models in autonomous driving systems: a systematic review","volume":"57","author":"Badjie","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.133503_bib38","article-title":"Adversarial attacks on neural network policies","author":"Huang","year":"2017","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib39","article-title":"Adversarial robust deep reinforcement learning requires redefining robustness","author":"Korkmaz","year":"2023","journal-title":"Proc. Proc. AAAI Conf. Artif. Intell. F."},{"issue":"1","key":"10.1016\/j.neucom.2026.133503_bib40","doi-asserted-by":"crossref","first-page":"758","DOI":"10.1109\/TDSC.2022.3143566","article-title":"Attacking deep reinforcement learning with decoupled adversarial policy","volume":"20","author":"Mo","year":"2022","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"issue":"5","key":"10.1016\/j.neucom.2026.133503_bib41","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3708320","article-title":"Adversarial machine learning attacks and defences in multi-agent reinforcement learning","volume":"57","author":"Standen","year":"2025","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.133503_bib42","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.127191","article-title":"Enhancing the robustness of QMIX against state-adversarial attacks","volume":"572","author":"Guo","year":"2024","journal-title":"Neurocomputing"},{"issue":"11","key":"10.1016\/j.neucom.2026.133503_bib43","doi-asserted-by":"crossref","first-page":"7115","DOI":"10.1109\/TCYB.2022.3225236","article-title":"False data-injection attack detection in cyber\u2013physical systems with unknown parameters: a deep reinforcement learning approach","volume":"53","author":"Liu","year":"2022","journal-title":"IEEE Trans. Cybern."},{"key":"10.1016\/j.neucom.2026.133503_bib44","article-title":"Robust reinforcement learning on state observations with learned optimal adversary","author":"Zhang","year":"2021","journal-title":"arXiv Prepr."},{"issue":"1","key":"10.1016\/j.neucom.2026.133503_bib45","doi-asserted-by":"crossref","first-page":"276","DOI":"10.3390\/make4010013","article-title":"Robust reinforcement learning: a review of foundations and recent advances","volume":"4","author":"Moos","year":"2022","journal-title":"Mach. Learn. Knowl. Extr."},{"issue":"2","key":"10.1016\/j.neucom.2026.133503_bib46","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1162\/0899766053011528","article-title":"Robust reinforcement learning","volume":"17","author":"Morimoto","year":"2005","journal-title":"Neural Comput."},{"key":"10.1016\/j.neucom.2026.133503_bib47","article-title":"Efficient action robust reinforcement learning with probabilistic policy execution uncertainty","author":"Liu","year":"2023","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib48","article-title":"Optimal transport perturbations for safe reinforcement learning with robustness guarantees","author":"Queeney","year":"2023","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib49","series-title":"Proceedings of the Machine Learning and Data Mining in Pattern Recognition: 13th International Conference, MLDM 2017","article-title":"Vulnerability of deep reinforcement learning to policy induction attacks","author":"Behzadan","year":"2017"},{"key":"10.1016\/j.neucom.2026.133503_bib50","series-title":"Proceedings of the 2022 10th International Conference on Intelligent Computing and Wireless Optical Communications (ICWOC), F","article-title":"Precise key frames adversarial attack against deep reinforcement learning","author":"Fan","year":"2022"},{"key":"10.1016\/j.neucom.2026.133503_bib51","first-page":"21024","article-title":"Robust deep reinforcement learning against adversarial perturbations on state observations","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"5","key":"10.1016\/j.neucom.2026.133503_bib52","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-021-3688-y","article-title":"Understanding adversarial attacks on observations in deep reinforcement learning","volume":"67","author":"Qiaoben","year":"2024","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133503_bib53","series-title":"Proceedings of the Proceedings of the Real-World Sequential Decision Making Workshop","article-title":"Manipulating neural policies with adversarial observations","author":"Hussenot","year":"2019"},{"key":"10.1016\/j.neucom.2026.133503_bib54","article-title":"Behavior-targeted attack on reinforcement learning with limited access to victim's policy","author":"Yamabe","year":"2024","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib55","series-title":"Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, F","article-title":"Exploring the training robustness of distributional reinforcement learning against noisy state observations","author":"Sun","year":"2023"},{"key":"10.1016\/j.neucom.2026.133503_bib56","series-title":"Proceedings of the Proceedings of the 15th ACM Asia conference on computer and communications security, F","article-title":"Adversarial attack against deep reinforcement learning with static reward impact map","author":"Chan","year":"2020"},{"issue":"5","key":"10.1016\/j.neucom.2026.133503_bib57","doi-asserted-by":"crossref","first-page":"4188","DOI":"10.1109\/TDSC.2022.3207429","article-title":"MARNet: Backdoor attacks against cooperative multi-agent reinforcement learning","volume":"20","author":"Chen","year":"2022","journal-title":"IEEE Trans. Dependable Secur. Comput."},{"key":"10.1016\/j.neucom.2026.133503_bib58","series-title":"Proceedings of the Proceedings of the 20th International Conference on Autonomous Agents and Multiagent Systems, F","article-title":"Transferable environment poisoning: training-time attack on reinforcement learning","author":"Xu","year":"2021"},{"key":"10.1016\/j.neucom.2026.133503_bib59","series-title":"Proceedings of the International Conference on Machine Learning, F","article-title":"Policy teaching via environment poisoning: training-time adversarial attacks against reinforcement learning","author":"Rakhsha","year":"2020"},{"key":"10.1016\/j.neucom.2026.133503_bib60","article-title":"Poisoning the well: can we simultaneously attack a group of learning agents?","author":"Bector","year":"2023","journal-title":"Proc. IJCAI F."},{"key":"10.1016\/j.neucom.2026.133503_bib61","article-title":"Local environment poisoning attacks on federated reinforcement learning","author":"Ma","year":"2023","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib62","article-title":"Detecting and mitigating reward hacking in reinforcement learning systems: a comprehensive empirical study","author":"Shihab","year":"2025","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib63","series-title":"Proceedings of the Sixteenth European Workshop on Reinforcement Learning, F","article-title":"Overcoming policy collapse in deep reinforcement learning","author":"Dohare","year":"2023"},{"key":"10.1016\/j.neucom.2026.133503_bib64","series-title":"Proceedings of the Aaai Conference on Artificial Intelligence, F","article-title":"Reward poisoning attacks on offline multi-agent reinforcement learning","author":"Wu","year":"2023"},{"key":"10.1016\/j.neucom.2026.133503_bib65","article-title":"Rlhfpoison: Reward poisoning attack for reinforcement learning with human feedback in large language models","author":"Wang","year":"2024","journal-title":"arXiv Prepr"},{"key":"10.1016\/j.neucom.2026.133503_bib66","series-title":"Proceedings of the International Conference on Decision and Game Theory for Security","article-title":"Reward delay attacks on deep reinforcement learning","author":"Sarkar","year":"2022"},{"key":"10.1016\/j.neucom.2026.133503_bib67","article-title":"Universal black-box reward poisoning attack against offline reinforcement learning","author":"Xu","year":"2024","journal-title":"arXiv Prepr"},{"key":"10.1016\/j.neucom.2026.133503_bib68","series-title":"Proceedings of the AAAI conference on artificial intelligence, F","article-title":"Spatiotemporally constrained action space attacks on deep reinforcement learning agents","author":"Lee","year":"2020"},{"key":"10.1016\/j.neucom.2026.133503_bib69","article-title":"Provably efficient action-manipulation attack against continuous reinforcement learning","author":"Luo","year":"2024","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib70","doi-asserted-by":"crossref","DOI":"10.1109\/TSMC.2024.3454118","article-title":"Adversarial attacks on multiagent deep reinforcement learning models in continuous action space","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"key":"10.1016\/j.neucom.2026.133503_bib71","article-title":"Adversarial exploitation of policy imitation","author":"Behzadan","year":"2019","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib72","series-title":"Proceedings of the 2021 ACM Asia Conference on Computer and Communications Security, F","article-title":"Stealing deep reinforcement learning models for fun and profit","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.133503_bib73","article-title":"Stealthy imitation: reward-guided environment-free policy stealing","author":"Zhuang","year":"2024","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib74","series-title":"proceedings of the Uncertainty in Artificial Intelligence, F","article-title":"Investigating vulnerabilities of deep neural policies","author":"Korkmaz","year":"2021"},{"key":"10.1016\/j.neucom.2026.133503_bib75","article-title":"Delving into adversarial attacks on deep policies","author":"Kos","year":"2017","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib76","series-title":"Proceedings of the International Conference on Machine Learning, F","article-title":"Towards robust and safe reinforcement learning with benign off-policy data","author":"Liu","year":"2023"},{"key":"10.1016\/j.neucom.2026.133503_bib77","article-title":"Rerogcrl: Representation-based robustness in goal-conditioned reinforcement learning","author":"Yin","year":"2023","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib78","series-title":"Proceedings of the NOMS 2024-2024 IEEE Network Operations and Management Symposium, F","article-title":"Routing optimization based on DRL and generative adversarial networks for SDN environments","author":"Altamirano","year":"2024"},{"key":"10.1016\/j.neucom.2026.133503_bib79","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.future.2023.09.011","article-title":"Deep reinforcement learning based evasion generative adversarial network for botnet detection","volume":"150","author":"Randhawa","year":"2024","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.neucom.2026.133503_bib80","article-title":"EVAGAN: evasion generative adversarial network for low data regimes","author":"Randhawa","year":"2021","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib81","series-title":"Proceedings of the NOMS 2024-2024 IEEE Network Operations and Management Symposium, F","article-title":"DRL meets GNN to improve QoS in Tactical MANETs","author":"Loevenich","year":"2024"},{"key":"10.1016\/j.neucom.2026.133503_bib82","series-title":"Proceedings of the MILCOM 2023-2023 IEEE Military Communications Conference (MILCOM), F","article-title":"Cooperative agent system for quantifying link robustness in tactical networks","author":"Loevenich","year":"2023"},{"key":"10.1016\/j.neucom.2026.133503_bib83","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125389","article-title":"Enhancing air traffic control: a transparent deep reinforcement learning framework for autonomous conflict resolution","volume":"260","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.133503_bib84","series-title":"Proceedings of the International conference on machine learning, F","article-title":"Robust adversarial reinforcement learning","author":"Pinto","year":"2017"},{"key":"10.1016\/j.neucom.2026.133503_bib85","article-title":"Wasserstein robust reinforcement learning","author":"Abdullah","year":"2019","journal-title":"arXiv Prepr"},{"key":"10.1016\/j.neucom.2026.133503_bib86","series-title":"Proceedings of the 2024 IEEE PES Innovative Smart Grid Technologies Europe (ISGT EUROPE), F","article-title":"Play with me: towards explaining the benefits of autocurriculum training of learning agents","author":"Veith","year":"2024"},{"key":"10.1016\/j.neucom.2026.133503_bib87","doi-asserted-by":"crossref","DOI":"10.1016\/j.apenergy.2025.125333","article-title":"Deep reinforcement learning based hierarchical energy management for virtual power plant with aggregated multiple heterogeneous microgrids","volume":"382","author":"Li","year":"2025","journal-title":"Appl. Energy"},{"key":"10.1016\/j.neucom.2026.133503_bib88","article-title":"A deep reinforcement learning approach using asymmetric self-play for robust multirobot flocking","author":"Jia","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"key":"10.1016\/j.neucom.2026.133503_bib89","article-title":"Reinforcement learning-based approaches for enhancing security and resilience in smart control: a survey on attack and defense methods","author":"Zhang","year":"2024","journal-title":"arXiv Prepr"},{"key":"10.1016\/j.neucom.2026.133503_bib90","series-title":"proceedings of the 2019 International Conference on Robotics and Automation (ICRA), F","article-title":"Robustness to out-of-distribution inputs via task-aware generative uncertainty","author":"Mcallister","year":"2019"},{"key":"10.1016\/j.neucom.2026.133503_bib91","series-title":"proceedings of the International Conference on Computer Safety, Reliability, and Security, F","article-title":"Mitigation of policy manipulation attacks on deep q-networks with parameter-space noise","author":"Behzadan","year":"2018"},{"key":"10.1016\/j.neucom.2026.133503_bib92","series-title":"Proceedings of the 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), F","article-title":"Adversarially robust policy learning: Active construction of physically-plausible perturbations","author":"Mandlekar","year":"2017"},{"issue":"9","key":"10.1016\/j.neucom.2026.133503_bib93","doi-asserted-by":"crossref","first-page":"2805","DOI":"10.1109\/TNNLS.2018.2886017","article-title":"Adversarial examples: attacks and defenses for deep learning","volume":"30","author":"Yuan","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.neucom.2026.133503_bib94","article-title":"Towards deep learning models resistant to transfer-based adversarial attacks via data-centric robust learning","author":"Yang","year":"2023","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib95","article-title":"Defense against reward poisoning attacks in reinforcement learning","author":"Banihashem","year":"2021","journal-title":"arXiv Prepr"},{"key":"10.1016\/j.neucom.2026.133503_bib96","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Reinforcement learning with perturbed rewards","author":"Wang","year":"2020"},{"key":"10.1016\/j.neucom.2026.133503_bib97","article-title":"Distributionally robust reinforcement learning","author":"Smirnova","year":"2019","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib98","series-title":"Proceedings of the International Conference on Machine Learning, F","article-title":"Action robust reinforcement learning and applications in continuous control","author":"Tessler","year":"2019"},{"key":"10.1016\/j.neucom.2026.133503_bib99","first-page":"26156","article-title":"Robust deep reinforcement learning through adversarial loss","volume":"34","author":"Oikarinen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4","key":"10.1016\/j.neucom.2026.133503_bib100","doi-asserted-by":"crossref","first-page":"5816","DOI":"10.1109\/JIOT.2023.3308260","article-title":"Promoting or hindering: stealthy black-box attacks against drl-based traffic signal control","volume":"11","author":"Ren","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.neucom.2026.133503_bib101","series-title":"Proceedings of the European Symposium on Research in Computer Security, F","article-title":"Real-time adversarial perturbations against deep reinforcement learning policies: attacks and defenses","author":"Tekgul","year":"2022"},{"key":"10.1016\/j.neucom.2026.133503_bib102","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence, F","article-title":"Training a resilient q-network against observational interference","author":"Yang","year":"2022"},{"key":"10.1016\/j.neucom.2026.133503_bib103","series-title":"Proceedings of the International Conference on Machine Learning, F","article-title":"Detecting adversarial directions in deep reinforcement learning to make robust decisions","author":"Korkmaz","year":"2023"},{"key":"10.1016\/j.neucom.2026.133503_bib104","series-title":"Proceedings of the 2018 IEEE third international conference on data science in cyberspace (DSC), F","article-title":"A PCA-based model to predict adversarial examples on Q-learning of path finding","author":"Xiang","year":"2018"},{"key":"10.1016\/j.neucom.2026.133503_bib105","article-title":"Adversarial behavior exclusion for safe reinforcement learning","author":"Rahman","year":"2023","journal-title":"Proc. IJCAI F."},{"key":"10.1016\/j.neucom.2026.133503_bib106","series-title":"Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems, F","doi-asserted-by":"crossref","DOI":"10.65109\/DMRA5778","article-title":"Memory-based resilient control against non-cooperation in multi-agent flocking","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.133503_bib107","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib108","series-title":"Proceedings of the 2016 IEEE symposium on security and privacy (SP), F","article-title":"Distillation as a defense to adversarial perturbations against deep neural networks","author":"Papernot","year":"2016"},{"key":"10.1016\/j.neucom.2026.133503_bib109","series-title":"Proceedings of the Proceedings of the 17th ACM Conference on Security and Privacy in Wireless and Mobile Networks, F","article-title":"System-level analysis of adversarial attacks and defenses on intelligence in O-RAN based cellular networks","author":"Chiejina","year":"2024"},{"key":"10.1016\/j.neucom.2026.133503_bib110","unstructured":"A. A. Rusu, S. G. Colmenarejo, C. Gulcehre, et al., Policy distillation, arXiv Prepr. (2015) arXiv:151106295."},{"key":"10.1016\/j.neucom.2026.133503_bib111","article-title":"Defending adversarial attacks without adversarial attacks in deep reinforcement learning","author":"Qu","year":"2020","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib112","article-title":"Defensive distillation is not robust to adversarial examples [J]","author":"Carlini","year":"2016","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib113","series-title":"Proceedings of the The 22nd international conference on artificial intelligence and statistics, F","article-title":"Distilling policy distillation","author":"Czarnecki","year":"2019"},{"key":"10.1016\/j.neucom.2026.133503_bib114","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1109\/OJITS.2021.3118972","article-title":"Adversarial attacks and defense in deep reinforcement learning (DRL)-based traffic signal controllers","volume":"2","author":"Haydari","year":"2021","journal-title":"IEEE Open J. Intell. Transp. Syst."},{"key":"10.1016\/j.neucom.2026.133503_bib115","series-title":"Proceedings of the International conference on machine learning, F","article-title":"Leveraging procedural generation to benchmark reinforcement learning","author":"Cobbe","year":"2020"},{"key":"10.1016\/j.neucom.2026.133503_bib116","series-title":"Proceedings of the Conference on robot learning, F","article-title":"Meta-world: a benchmark and evaluation for multi-task and meta reinforcement learning","author":"Yu","year":"2020"},{"key":"10.1016\/j.neucom.2026.133503_bib117","article-title":"Deepmind control suite","author":"Tassa","year":"2018","journal-title":"arXiv Prepr."},{"key":"10.1016\/j.neucom.2026.133503_bib118","series-title":"Proceedings of the IEEE\/CVF international conference on computer vision, F","article-title":"Habitat: a platform for embodied ai research","author":"Savva","year":"2019"},{"key":"10.1016\/j.neucom.2026.133503_bib119","first-page":"37567","article-title":"Smacv2: an improved benchmark for cooperative multi-agent reinforcement learning","volume":"36","author":"Ellis","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"4","key":"10.1016\/j.neucom.2026.133503_bib120","doi-asserted-by":"crossref","first-page":"11142","DOI":"10.1109\/LRA.2022.3196132","article-title":"Safe-control-gym: a unified benchmark suite for safe learning-based control and reinforcement learning in robotics","volume":"7","author":"Yuan","year":"2022","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.neucom.2026.133503_bib121","first-page":"18964","article-title":"Safety gymnasium: a unified safe reinforcement learning benchmark","volume":"36","author":"Ji","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.133503_bib122","doi-asserted-by":"crossref","DOI":"10.1145\/3779424","article-title":"RS-DRL: managing uncertainty in self-adaptive systems based on a novel continuous deep reinforcement learning method","author":"Kavianifar","year":"2025","journal-title":"ACM Trans. Auton. Adapt. Syst."},{"issue":"3","key":"10.1016\/j.neucom.2026.133503_bib123","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3631970","article-title":"Testing of deep reinforcement learning agents with surrogate models","volume":"33","author":"Biagiola","year":"2024","journal-title":"ACM Trans. Softw. Eng. Methodol."},{"key":"10.1016\/j.neucom.2026.133503_bib124","series-title":"Proceedings of the 2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), F","article-title":"Safe-assured learning-based deep SE (3) motion joint planning and control for UAV interactions with dynamic environments","author":"Zhang","year":"2024"},{"issue":"2","key":"10.1016\/j.neucom.2026.133503_bib125","first-page":"144","article-title":"Evaluating domain randomization techniques in DRL agents: a comparative study of normal, randomized, and non-randomized resets","author":"Elsafi","year":"2025","journal-title":"Comput. Model. Eng. Sci. (CMES)"},{"key":"10.1016\/j.neucom.2026.133503_bib126","article-title":"Human-in-the-loop machine learning for safe and ethical autonomous vehicles: Principles, challenges, and opportunities","author":"Emami","year":"2024","journal-title":"arXiv Prepr."},{"issue":"23","key":"10.1016\/j.neucom.2026.133503_bib127","doi-asserted-by":"crossref","first-page":"38585","DOI":"10.1109\/JIOT.2024.3447070","article-title":"Ethical alignment decision making for connected autonomous vehicle in traffic dilemmas via reinforcement learning from human feedback","volume":"11","author":"Gao","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.neucom.2026.133503_bib128","series-title":"Proceedings of the AAAI conference on artificial intelligence, F","article-title":"Deep reinforcement learning policies learn shared adversarial features across mdps","author":"Korkmaz","year":"2022"},{"issue":"11","key":"10.1016\/j.neucom.2026.133503_bib129","doi-asserted-by":"crossref","first-page":"3325","DOI":"10.1007\/s13042-020-01242-z","article-title":"Adversarial examples: attacks and defenses in the physical world","volume":"12","author":"Ren","year":"2021","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.neucom.2026.133503_bib130","doi-asserted-by":"crossref","DOI":"10.1109\/JIOT.2024.3423022","article-title":"Deep reinforcement learning based self-evolving moving target defense approach against unknown attacks","author":"Cao","year":"2024","journal-title":"IEEE Internet Things J."},{"issue":"4","key":"10.1016\/j.neucom.2026.133503_bib131","doi-asserted-by":"crossref","first-page":"2245","DOI":"10.1109\/COMST.2023.3319492","article-title":"Adversarial attacks and defenses in machine learning-empowered communication systems and networks: a contemporary survey","volume":"25","author":"Wang","year":"2023","journal-title":"IEEE Commun. Surv. & Tutor."},{"issue":"10","key":"10.1016\/j.neucom.2026.133503_bib132","doi-asserted-by":"crossref","first-page":"4381","DOI":"10.1109\/TIV.2023.3296227","article-title":"Robust adversarial attacks detection based on explainable deep reinforcement learning for UAV guidance and planning","volume":"8","author":"Hickling","year":"2023","journal-title":"IEEE Trans. Intell. Veh."},{"key":"10.1016\/j.neucom.2026.133503_bib133","series-title":"Proceedings of the AAAI conference on artificial intelligence","article-title":"Adversarially robust distillation","author":"Goldblum","year":"2020"},{"key":"10.1016\/j.neucom.2026.133503_bib134","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2025.126752","article-title":"Adaptive precision layering for efficient adversarial training of deep learning models in intelligent vehicles","volume":"272","author":"Hussain","year":"2025","journal-title":"Expert Syst. Appl."},{"issue":"4","key":"10.1016\/j.neucom.2026.133503_bib135","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-023-3853-y","article-title":"Robust cooperative multi-agent reinforcement learning via multi-view message certification","volume":"67","author":"Yuan","year":"2024","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.neucom.2026.133503_bib136","article-title":"Game-theoretic robust reinforcement learning handles temporally coupled perturbations","author":"Liang","year":"2023","journal-title":"arXiv Prepr"},{"issue":"12","key":"10.1016\/j.neucom.2026.133503_bib137","doi-asserted-by":"crossref","first-page":"17549","DOI":"10.1109\/TNNLS.2023.3305983","article-title":"Hierarchical adversarial inverse reinforcement learning","volume":"35","author":"Chen","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"10.1016\/j.neucom.2026.133503_bib138","doi-asserted-by":"crossref","first-page":"362","DOI":"10.17775\/CSEEJPES.2018.00520","article-title":"Review on the research and practice of deep learning and reinforcement learning in smart grids","volume":"4","author":"Zhang","year":"2018","journal-title":"CSEE J. Power Energy Syst."},{"issue":"11","key":"10.1016\/j.neucom.2026.133503_bib139","doi-asserted-by":"crossref","first-page":"2892","DOI":"10.3390\/diagnostics12112892","article-title":"An Al-Biruni earth radius optimization-based deep convolutional neural network for classifying monkeypox disease","volume":"12","author":"Khafaga","year":"2022","journal-title":"Diagnostics"},{"key":"10.1016\/j.neucom.2026.133503_bib140","article-title":"Temporal adversarial attacks on time series and reinforcement learning systems: a systematic survey","author":"Kurniawan","year":"2026","journal-title":"Taxon. Benchmark Roadmap"},{"key":"10.1016\/j.neucom.2026.133503_bib141","unstructured":"Corsi D., Amir G., Katz G., et al. Analyzing adversarial inputs in deep reinforcement learning (2024) [J]. Technical Report, 2024."},{"issue":"7","key":"10.1016\/j.neucom.2026.133503_bib142","doi-asserted-by":"crossref","first-page":"6392","DOI":"10.1109\/JIOT.2020.2974281","article-title":"Deep reinforcement learning for resource protection and real-time detection in IoT environment","volume":"7","author":"Liang","year":"2020","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.neucom.2026.133503_bib143","article-title":"Image quality assessment: exploring the similarity of deep features via covariance-constrained spectra","author":"Lang","year":"2025","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.neucom.2026.133503_bib144","doi-asserted-by":"crossref","first-page":"108489","DOI":"10.1016\/j.future.2026.108489","article-title":"A trust-aware and cost-optimized blockchain oracle selection model with deep reinforcement learning","author":"Zhang","year":"2026","journal-title":"Future Gener. Comput. Syst."},{"issue":"1","key":"10.1016\/j.neucom.2026.133503_bib145","first-page":"31","article-title":"Hardware level countermeasures for adversarial attacks in machine learning devices","volume":"1","author":"Raheem","year":"2024","journal-title":"J. Data Digit. Innov. (JDDI)"},{"key":"10.1016\/j.neucom.2026.133503_bib146","series-title":"Proceedings of the 2024 IEEE 99th Vehicular Technology Conference (VTC2024-Spring), F","article-title":"RIS-assisted integrated sensing and communication system with physical layer security enhancement by DRL approach","author":"Jiang","year":"2024"},{"issue":"2","key":"10.1016\/j.neucom.2026.133503_bib147","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1109\/TAI.2021.3111139","article-title":"Challenges and countermeasures for adversarial attacks on deep reinforcement learning","volume":"3","author":"Ilahi","year":"2021","journal-title":"IEEE Trans. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.133503_bib148","article-title":"Adversarial machine learning: A taxonomy and terminology of attacks and mitigations","author":"Oprea","year":"2023","journal-title":"Natl. Inst. Stand. Technol."},{"key":"10.1016\/j.neucom.2026.133503_bib149","doi-asserted-by":"crossref","first-page":"359","DOI":"10.1613\/jair.1.15348","article-title":"Human-in-the-loop reinforcement learning: A survey and position on requirements, challenges, and opportunities","volume":"79","author":"Retzlaff","year":"2024","journal-title":"J. Artif. Intell. Res."},{"key":"10.1016\/j.neucom.2026.133503_bib150","doi-asserted-by":"crossref","DOI":"10.34190\/icair.4.1.3194","article-title":"Governance considerations of adversarial attacks on AI Systems","author":"Lekota","year":"2024","journal-title":"Int. Conf. AI Res."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009008?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226009008?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T19:20:30Z","timestamp":1777576830000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226009008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7]]},"references-count":150,"alternative-id":["S0925231226009008"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133503","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,7]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing security in deep reinforcement learning: A comprehensive survey on adversarial attacks and defenses","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.133503","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"133503"}}