{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T17:38:16Z","timestamp":1783186696152,"version":"3.54.6"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031264085","type":"print"},{"value":"9783031264092","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\/978-3-031-26409-2_15","type":"book-chapter","created":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T09:04:46Z","timestamp":1678957486000},"page":"235-250","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Defending Observation Attacks in\u00a0Deep Reinforcement Learning via\u00a0Detection and\u00a0Denoising"],"prefix":"10.1007","author":[{"given":"Zikang","family":"Xiong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joe","family":"Eappen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suresh","family":"Jagannathan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,3,17]]},"reference":[{"key":"15_CR1","unstructured":"Achiam, J., Held, D., Tamar, A., Abbeel, P.: Constrained policy optimization. In: International Conference on Machine Learning, pp. 22\u201331. PMLR (2017)"},{"key":"15_CR2","unstructured":"Doersch, C.: Tutorial on variational autoencoders. arXiv preprint arXiv:1606.05908 (2016)"},{"key":"15_CR3","unstructured":"Fujimoto, S., Hoof, H., Meger, D.: Addressing function approximation error in actor-critic methods. In: ICML (2018)"},{"key":"15_CR4","unstructured":"Gleave, A., Dennis, M., Wild, C., Kant, N., Levine, S., Russell, S.: Adversarial policies: attacking deep reinforcement learning. arXiv:1905.10615 (2019)"},{"key":"15_CR5","unstructured":"Havens, A.J., Jiang, Z., Sarkar, S.: Online robust policy learning in the presence of unknown adversaries. arXiv preprint arXiv:1807.06064 (2018)"},{"key":"15_CR6","unstructured":"Huang, S., Papernot, N., Goodfellow, I., Duan, Y., Abbeel, P.: Adversarial attacks on neural network policies. arXiv preprint arXiv:1702.02284 (2017)"},{"issue":"2","key":"15_CR7","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1287\/moor.1040.0129","volume":"30","author":"GN Iyengar","year":"2005","unstructured":"Iyengar, G.N.: Robust dynamic programming. Math. Oper. Res. 30(2), 257\u2013280 (2005)","journal-title":"Math. Oper. Res."},{"issue":"7","key":"15_CR8","doi-asserted-by":"publisher","first-page":"855","DOI":"10.1177\/0278364912444543","volume":"31","author":"M Kobilarov","year":"2012","unstructured":"Kobilarov, M.: Cross-entropy motion planning. Int. J. Robot. Res. 31(7), 855\u2013871 (2012)","journal-title":"Int. J. Robot. Res."},{"key":"15_CR9","unstructured":"Kos, J., Song, D.: Delving into adversarial attacks on deep policies. arXiv preprint arXiv:1705.06452 (2017)"},{"key":"15_CR10","unstructured":"Li, B., Chen, C., Wang, W., Carin, L.: Certified adversarial robustness with additive noise. arXiv preprint arXiv:1809.03113 (2018)"},{"key":"15_CR11","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":"15_CR12","unstructured":"Malhotra, P., Ramakrishnan, A., Anand, G., Vig, L., Agarwal, P., Shroff, G.: LSTM-based encoder-decoder for multi-sensor anomaly detection. arXiv preprint arXiv:1607.00148 (2016)"},{"key":"15_CR13","doi-asserted-by":"crossref","unstructured":"Mandlekar, A., Zhu, Y., Garg, A., Fei-Fei, L., Savarese, S.: Adversarially robust policy learning: active construction of physically-plausible perturbations. In: IEEE\/RSJ IROS, pp. 3932\u20133939. IEEE (2017)","DOI":"10.1109\/IROS.2017.8206245"},{"key":"15_CR14","unstructured":"Panda, P., Roy, K.: Implicit generative modeling of random noise during training for adversarial robustness. arXiv preprint arXiv:1807.02188 (2018)"},{"issue":"3","key":"15_CR15","doi-asserted-by":"publisher","first-page":"1544","DOI":"10.1109\/LRA.2018.2801475","volume":"3","author":"D Park","year":"2018","unstructured":"Park, D., Hoshi, Y., Kemp, C.C.: A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder. IEEE Robot. Autom. Lett. 3(3), 1544\u20131551 (2018)","journal-title":"IEEE Robot. Autom. Lett."},{"key":"15_CR16","unstructured":"Pattanaik, A., Tang, Z., Liu, S., Bommannan, G., Chowdhary, G.: Robust deep reinforcement learning with adversarial attacks. arXiv preprint arXiv:1712.03632 (2017)"},{"key":"15_CR17","unstructured":"Raffin, A.: RL baselines3 Zoo (2020). https:\/\/github.com\/DLR-RM\/rl-baselines3-zoo"},{"key":"15_CR18","unstructured":"Rajeswaran, A., Ghotra, S., Ravindran, B., Levine, S.: EPOpt: learning robust neural network policies using model ensembles. arXiv preprint arXiv:1610.01283 (2016)"},{"key":"15_CR19","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)"},{"key":"15_CR20","doi-asserted-by":"crossref","unstructured":"Sun, J., et al.: Stealthy and efficient adversarial attacks against deep reinforcement learning. In: AAAI (2020)","DOI":"10.1609\/aaai.v34i04.6047"},{"key":"15_CR21","unstructured":"Tessler, C., Efroni, Y., Mannor, S.: Action robust reinforcement learning and applications in continuous control. In: ICML, pp. 6215\u20136224. PMLR (2019)"},{"key":"15_CR22","doi-asserted-by":"crossref","unstructured":"Todorov, E., Erez, T., Tassa, Y.: MuJoCo: a physics engine for model-based control. In: 2012 IEEE\/RSJ International Conference on Intelligent Robots and Systems (2012)","DOI":"10.1109\/IROS.2012.6386109"},{"key":"15_CR23","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: ICML (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"15_CR24","unstructured":"Xiong, Z., Eappen, J., Zhu, H., Jagannathan, S.: Robustness to adversarial attacks in learning-enabled controllers. arXiv preprint arXiv:2006.06861 (2020)"},{"key":"15_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, C., et al.: A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33011409"},{"key":"15_CR26","unstructured":"Zhang, H., Chen, H., Boning, D., Hsieh, C.J.: Robust reinforcement learning on state observations with learned optimal adversary. arXiv:2101.08452 (2021)"},{"key":"15_CR27","unstructured":"Zhang, H., et al.: Robust deep reinforcement learning against adversarial perturbations on state observations. arXiv:2003.08938 (2020)"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-26409-2_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,16]],"date-time":"2023-03-16T09:25:26Z","timestamp":1678958726000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-26409-2_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031264085","9783031264092"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-26409-2_15","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":"17 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Grenoble","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","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":"19 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2022.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1060","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":"236","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":"22% - 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":"3-4","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":"3-4","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)"}},{"value":"17 demo track papers have been accepted from 28 submissions","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}