{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,14]],"date-time":"2026-04-14T15:52:45Z","timestamp":1776181965350,"version":"3.50.1"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031263682","type":"print"},{"value":"9783031263699","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-26369-9_11","type":"book-chapter","created":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T12:43:17Z","timestamp":1675860197000},"page":"212-230","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Reward Delay Attacks on\u00a0Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"given":"Anindya","family":"Sarkar","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiarui","family":"Feng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yevgeniy","family":"Vorobeychik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Christopher","family":"Gill","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,2,9]]},"reference":[{"key":"11_CR1","unstructured":"ACM: American center for mobility (2022). https:\/\/www.acmwillowrun.org\/"},{"issue":"91","key":"11_CR2","first-page":"1","volume":"20","author":"J Altschuler","year":"2019","unstructured":"Altschuler, J., Brunel, V.E., Malek, A.: Best arm identification for contaminated bandits. J. Mach. Learn. Res. 20(91), 1\u201339 (2019)","journal-title":"J. Mach. Learn. Res."},{"key":"11_CR3","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1007\/978-3-319-62416-7_19","volume-title":"Machine Learning and Data Mining in Pattern Recognition","author":"V Behzadan","year":"2017","unstructured":"Behzadan, V., Munir, A.: Vulnerability of deep reinforcement learning to policy induction attacks. In: Perner, P. (ed.) MLDM 2017. LNCS (LNAI), vol. 10358, pp. 262\u2013275. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-62416-7_19"},{"key":"11_CR4","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1613\/jair.3912","volume":"47","author":"MG Bellemare","year":"2013","unstructured":"Bellemare, M.G., Naddaf, Y., Veness, J., Bowling, M.: The arcade learning environment: an evaluation platform for general agents. J. Artif. Intell. Res. 47, 253\u2013279 (2013)","journal-title":"J. Artif. Intell. Res."},{"key":"11_CR5","doi-asserted-by":"crossref","unstructured":"Bla\u00df, T., Casini, D., Bozhko, S., Brandenburg, B.: A ROS 2 response-time analysis exploiting starvation freedom and execution-time variance. In: Proceedings of the 42nd IEEE Real-Time Systems Symposium (RTSS), pp. 41\u201353 (2021)","DOI":"10.1109\/RTSS52674.2021.00016"},{"key":"11_CR6","doi-asserted-by":"crossref","unstructured":"Bla\u00df, T., Hamann, A., Lange, R., Ziegenbein, D., Brandenburg, B.: Automatic latency management for ROS 2: benefits, challenges, and open problems. In: Proceedings of the 27th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS), pp. 264\u2013277 (2021)","DOI":"10.1109\/RTAS52030.2021.00029"},{"key":"11_CR7","unstructured":"Brockman, G., et al.: Openai gym. arXiv preprint arXiv:1606.01540 (2016)"},{"key":"11_CR8","unstructured":"Casini, D., Bla\u00df, T., L\u00fctkebohle, I., Brandenburg, B.: Response-time analysis of ROS 2 processing chains under reservation-based scheduling. In: Proceedings of the 31st Euromicro Conference on Real-Time Systems (ECRTS), pp. 6:1\u20136:23 (2019)"},{"key":"11_CR9","doi-asserted-by":"crossref","unstructured":"Choi, H., Xiang, Y., Kim, H.: PiCAS: new design of priority- driven chain-aware scheduling for ROS2. In: Proceedings of the 27th IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS) (2021)","DOI":"10.1109\/RTAS52030.2021.00028"},{"key":"11_CR10","unstructured":"Chung, K., et al.: Smart malware that uses leaked control data of robotic applications: the case of Raven-II surgical robots. In: 22nd International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2019), pp. 337\u2013351. USENIX Association, Chaoyang District, Beijing, September 2019. https:\/\/www.usenix.org\/conference\/raid2019\/presentation\/chung"},{"key":"11_CR11","doi-asserted-by":"crossref","unstructured":"DeMarinis, N., Tellex, S., Kemerlis, V.P., Konidaris, G., Fonseca, R.: Scanning the internet for ROS: a view of security in robotics research. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 8514\u20138521. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794451"},{"key":"11_CR12","doi-asserted-by":"crossref","unstructured":"Dieber, B., Kacianka, S., Rass, S., Schartner, P.: Application-level security for ros-based applications. In: 2016 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4477\u20134482. IEEE (2016)","DOI":"10.1109\/IROS.2016.7759659"},{"key":"11_CR13","unstructured":"Dong, Y., et al.: Mcity data collection for automated vehicles study. arXiv preprint arXiv:1912.06258 (2019)"},{"key":"11_CR14","doi-asserted-by":"crossref","unstructured":"Garnett, N., Cohen, R., Pe\u2019er, T., Lahav, R., Levi, D.: 3D-lanenet: end-to-end 3d multiple lane detection. In: IEEE\/CVF International Conference on Computer Vision, pp. 2921\u20132930 (2019)","DOI":"10.1109\/ICCV.2019.00301"},{"key":"11_CR15","unstructured":"Huang, S., Papernot, N., Goodfellow, I., Duan, Y., Abbeel, P.: Adversarial attacks on neural network policies. arXiv preprint arXiv:1702.02284 (2017)"},{"key":"11_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1007\/978-3-030-32430-8_14","volume-title":"Decision and Game Theory for Security","author":"Y Huang","year":"2019","unstructured":"Huang, Y., Zhu, Q.: Deceptive reinforcement learning under adversarial manipulations on cost signals. In: Alpcan, T., Vorobeychik, Y., Baras, J.S., D\u00e1n, G. (eds.) GameSec 2019. LNCS, vol. 11836, pp. 217\u2013237. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32430-8_14"},{"key":"11_CR17","unstructured":"Jun, K.S., Li, L., Ma, Y., Zhu, J.: Adversarial attacks on stochastic bandits. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"11_CR18","unstructured":"Kiran, B.R., et al.: Deep reinforcement learning for autonomous driving: a survey. IEEE Trans. Intell. Transp. Syst. (2021)"},{"key":"11_CR19","doi-asserted-by":"crossref","unstructured":"Kocher, P., et al.: Spectre attacks: exploiting speculative execution. In: 2019 IEEE Symposium on Security and Privacy (SP), pp. 1\u201319. IEEE (2019)","DOI":"10.1109\/SP.2019.00002"},{"key":"11_CR20","unstructured":"Kos, J., Song, D.: Delving into adversarial attacks on deep policies. arXiv preprint arXiv:1705.06452 (2017)"},{"key":"11_CR21","doi-asserted-by":"crossref","unstructured":"Li, A., Wang, J., Zhang, N.: Chronos: timing interference as a new attack vector on autonomous cyber-physical systems. In: Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, pp. 2426\u20132428 (2021)","DOI":"10.1145\/3460120.3485350"},{"key":"11_CR22","doi-asserted-by":"crossref","unstructured":"Lin, Y.C., Hong, Z.W., Liao, Y.H., Shih, M.L., Liu, M.Y., Sun, M.: Tactics of adversarial attack on deep reinforcement learning agents. arXiv preprint arXiv:1703.06748 (2017)","DOI":"10.24963\/ijcai.2017\/525"},{"key":"11_CR23","unstructured":"Liu, F., Shroff, N.: Data poisoning attacks on stochastic bandits. In: International Conference on Machine Learning, pp. 4042\u20134050. PMLR (2019)"},{"key":"11_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Reinforcement learning for clinical decision support in critical care: comprehensive review. J. Med. Internet Res. 22(7), e18477 (2020)","DOI":"10.2196\/18477"},{"key":"11_CR25","unstructured":"Luo, M., Myers, A.C., Suh, G.E.: Stealthy tracking of autonomous vehicles with cache side channels. In: 29th USENIX Security Symposium (USENIX Security 20), pp. 859\u2013876 (2020)"},{"key":"11_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1007\/978-3-030-01554-1_11","volume-title":"Decision and Game Theory for Security","author":"Y Ma","year":"2018","unstructured":"Ma, Y., Jun, K.-S., Li, L., Zhu, X.: Data poisoning attacks in contextual bandits. In: Bushnell, L., Poovendran, R., Ba\u015far, T. (eds.) GameSec 2018. LNCS, vol. 11199, pp. 186\u2013204. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01554-1_11"},{"key":"11_CR27","doi-asserted-by":"crossref","unstructured":"Mahfouzi, R., Aminifar, A., Samii, S., Payer, M., Eles, P., Peng, Z.: Butterfly attack: adversarial manipulation of temporal properties of cyber-physical systems. In: 2019 IEEE Real-Time Systems Symposium (RTSS), pp. 93\u2013106. IEEE (2019)","DOI":"10.1109\/RTSS46320.2019.00019"},{"issue":"6419","key":"11_CR28","doi-asserted-by":"publisher","first-page":"1140","DOI":"10.1126\/science.aar6404","volume":"362","author":"D Silver","year":"2018","unstructured":"Silver, D., et al.: A general reinforcement learning algorithm that masters chess, shogi, and go through self-play. Science 362(6419), 1140\u20131144 (2018)","journal-title":"Science"},{"key":"11_CR29","unstructured":"STII: Illinois autonomous and connected track (2022). https:\/\/ict.illinois.edu\/i-act"},{"key":"11_CR30","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Response time analysis and priority assignment of processing chains on ROS2 executors. In: Proceedings of the 41st IEEE Real-Time Systems Symposium (RTSS) (2020)","DOI":"10.1109\/RTSS49844.2020.00030"},{"key":"11_CR31","doi-asserted-by":"crossref","unstructured":"Van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 30 (2016)","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"11_CR32","unstructured":"Wang, Z., Ren, W., Qiu, Q.: LaneNet: real-time lane detection networks for autonomous driving. arXiv preprint arXiv:1807.01726 (2018)"},{"key":"11_CR33","unstructured":"Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1995\u20132003. PMLR (2016)"},{"key":"11_CR34","unstructured":"Zhang, H., Parkes, D.C.: Value-based policy teaching with active indirect elicitation. In: AAAI, vol. 8, pp. 208\u2013214 (2008)"},{"key":"11_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, H., Parkes, D.C., Chen, Y.: Policy teaching through reward function learning. In: Proceedings of the 10th ACM Conference on Electronic Commerce, pp. 295\u2013304 (2009)","DOI":"10.1145\/1566374.1566417"},{"key":"11_CR36","unstructured":"Zhang, X., Ma, Y., Singla, A., Zhu, X.: Adaptive reward-poisoning attacks against reinforcement learning. In: International Conference on Machine Learning, pp. 11225\u201311234. PMLR (2020)"}],"container-title":["Lecture Notes in Computer Science","Decision and Game Theory for Security"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26369-9_11","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,8]],"date-time":"2023-02-08T13:08:47Z","timestamp":1675861727000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26369-9_11"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031263682","9783031263699"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26369-9_11","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"9 February 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"GameSec","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Decision and Game Theory for Security","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"PIttsburgh, PA","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"gamesec2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.gamesec-conf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"39","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"15","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"38% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}