{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T21:36:34Z","timestamp":1742938594777,"version":"3.40.3"},"publisher-location":"Cham","reference-count":36,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030688509"},{"type":"electronic","value":"9783030688516"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021]]},"DOI":"10.1007\/978-3-030-68851-6_2","type":"book-chapter","created":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T07:04:02Z","timestamp":1612422242000},"page":"19-43","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Attention Mechanism Based Adversarial Attack Against Deep Reinforcement Learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7153-2755","authenticated-orcid":false,"given":"Jinyin","family":"Chen","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2734-2249","authenticated-orcid":false,"given":"Xueke","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Haibin","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Shouling","family":"Ji","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,2,5]]},"reference":[{"key":"2_CR1","volume-title":"Reinforcement Learning: An Introduction","author":"RS Sutton","year":"2018","unstructured":"Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction. MIT Press, Cambridge (2018)"},{"key":"2_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/978-3-030-24907-6_26","volume-title":"Security, Privacy, and Anonymity in Computation, Communication, and Storage","author":"M Peters","year":"2019","unstructured":"Peters, M., Goltz, J., Wiedenmann, S., Mundt, T.: Using machine learning to find anomalies in field bus network traffic. In: Wang, G., Feng, J., Bhuiyan, M.Z.A., Lu, R. (eds.) SpaCCS 2019. LNCS, vol. 11611, pp. 336\u2013353. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-24907-6_26"},{"key":"2_CR3","unstructured":"Szegedy, C., et al.: Intriguing properties of neural networks. arXiv preprint arXiv:1312.6199 (2013)"},{"key":"2_CR4","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. arXiv preprint arXiv:1412.6572 (2014)"},{"key":"2_CR5","unstructured":"Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: International Conference on Machine Learning, pp. 1928\u20131937 (2016)"},{"key":"2_CR6","unstructured":"Huang, S., Papernot, N., Goodfellow, I., Duan, Y., Abbeel, P.: Adversarial attacks on neural network policies. arXiv preprint arXiv:1702.02284 (2017)"},{"key":"2_CR7","unstructured":"Bansal, T., Pachocki, J., Sidor, S., Sutskever, I., Mordatch, I.: Emergent complexity via multi-agent competition. arXiv preprint arXiv:1710.03748 (2017)"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Bai, X., Niu, W., Liu, J., Gao, X., Xiang, Y., Liu, J.: Adversarial examples construction towards white-box Q table variation in DQN pathfinding training. In: 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), pp. 781\u2013787. IEEE (2018)","DOI":"10.1109\/DSC.2018.00126"},{"key":"2_CR9","unstructured":"Chen, T., et al.: Gradient band-based adversarial training for generalized attack immunity of A3C path finding. arXiv preprint arXiv:1807.06752 (2018)"},{"key":"2_CR10","unstructured":"Inkawhich, M., Chen, Y., Li, H.: Snooping attacks on deep reinforcement learning. arXiv preprint arXiv:1905.11832 (2019)"},{"key":"2_CR11","unstructured":"Schulman, J., Levine, S., Abbeel, P., Jordan, M., Moritz, P.: Trust region policy optimization. In: International Conference on Machine Learning, pp. 1889\u20131897 (2015)"},{"key":"2_CR12","unstructured":"Lin, Y.-C., Liu, M.-Y., Sun, M., Huang, J.-B.: Detecting adversarial attacks on neural network policies with visual foresight. arXiv preprint arXiv:1710.00814 (2017)"},{"key":"2_CR13","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":"2_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"374","DOI":"10.1007\/978-3-319-89500-0_33","volume-title":"Information and Communications Security","author":"J Liu","year":"2018","unstructured":"Liu, J., et al.: A method to effectively detect vulnerabilities on path planning of VIN. In: Qing, S., Mitchell, C., Chen, L., Liu, D. (eds.) ICICS 2017. LNCS, vol. 10631, pp. 374\u2013384. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-89500-0_33"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Shumailov, I., Cui, H., Gao, X., Mullins, R., Anderson, R.: Blackbox attacks on reinforcement learning agents using approximated temporal information. arXiv preprint arXiv:1909.02918 (2019)","DOI":"10.1109\/DSN-W50199.2020.00013"},{"key":"2_CR16","unstructured":"Ebeling-Rump, M., Kao, M., Hervieux-Moore, Z.: Applying q-learning to flappy bird. Department of Mathematics and Statistics, Queens University (2016)"},{"key":"2_CR17","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1007\/978-3-319-72395-2_19","volume-title":"Security, Privacy, and Anonymity in Computation, Communication, and Storage","author":"K Ma","year":"2017","unstructured":"Ma, K., Jiang, R., Dong, M., Jia, Y., Li, A.: Neural network based web log analysis for web intrusion detection. In: Wang, G., Atiquzzaman, M., Yan, Z., Choo, K.-K.R. (eds.) SpaCCS 2017. LNCS, vol. 10658, pp. 194\u2013204. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-72395-2_19"},{"key":"2_CR18","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1007\/978-3-030-05345-1_43","volume-title":"Security, Privacy, and Anonymity in Computation, Communication, and Storage","author":"X Yan","year":"2018","unstructured":"Yan, X., Cui, B., Li, J.: Malicious domain name recognition based on deep neural networks. In: Wang, G., Chen, J., Yang, L.T. (eds.) SpaCCS 2018. LNCS, vol. 11342, pp. 497\u2013505. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-05345-1_43"},{"key":"2_CR19","unstructured":"Mnih, V., et al.: Playing atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013)"},{"issue":"7540","key":"2_CR20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/nature14236","volume":"518","author":"V Mnih","year":"2015","unstructured":"Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518(7540), 529\u2013533 (2015)","journal-title":"Nature"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.: Towards evaluating the robustness of neural networks. In: 2017 IEEE Symposium on Security and Privacy (SP), pp. 39\u201357. IEEE (2017)","DOI":"10.1109\/SP.2017.49"},{"key":"2_CR22","unstructured":"Kos, J., Song, D.: Delving into adversarial attacks on deep policies. arXiv preprint arXiv:1705.06452 (2017)"},{"key":"2_CR23","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":"2_CR24","doi-asserted-by":"crossref","unstructured":"Xiang, Y., Niu, W., Liu, J., Chen, T., Han, Z.: A PCA-based model to predict adversarial examples on q-learning of path finding. In: 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC), pp. 773\u2013780. IEEE (2018)","DOI":"10.1109\/DSC.2018.00125"},{"key":"2_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1007\/978-3-030-24900-7_7","volume-title":"Security, Privacy, and Anonymity in Computation, Communication, and Storage","author":"P Chatterjee","year":"2019","unstructured":"Chatterjee, P., Yalchin, A., Shelton, J., Roy, K., Yuan, X., Edoh, K.D.: Presentation attack detection using wavelet transform and deep residual neural net. In: Wang, G., Feng, J., Bhuiyan, M.Z.A., Lu, R. (eds.) SpaCCS 2019. LNCS, vol. 11637, pp. 86\u201394. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-24900-7_7"},{"key":"2_CR26","unstructured":"Tretschk, E., Oh, S.J., Fritz, M.: Sequential attacks on agents for long-term adversarial goals. arXiv preprint arXiv:1805.12487 (2018)"},{"key":"2_CR27","unstructured":"Russo, A., Proutiere, A.: Optimal attacks on reinforcement learning policies. arXiv preprint arXiv:1907.13548 (2019)"},{"key":"2_CR28","unstructured":"Gu, Z., Jia, Z., Choset, H.: Adversary A3C for robust reinforcement learning. arXiv preprint arXiv:1912.00330 (2019)"},{"key":"2_CR29","unstructured":"Fischer, M., Mirman, M., Vechev, M.: Online robustness training for deep reinforcement learning. arXiv preprint arXiv:1911.00887 (2019)"},{"key":"2_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1007\/978-3-319-99229-7_34","volume-title":"Computer Safety, Reliability, and Security","author":"V Behzadan","year":"2018","unstructured":"Behzadan, V., Munir, A.: Mitigation of policy manipulation attacks on deep q-networks with parameter-space noise. In: Gallina, B., Skavhaug, A., Schoitsch, E., Bitsch, F. (eds.) SAFECOMP 2018. LNCS, vol. 11094, pp. 406\u2013417. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-319-99229-7_34"},{"key":"2_CR31","unstructured":"Havens, A., Jiang, Z., Sarkar, S.: Online robust policy learning in the presence of unknown adversaries. In: Advances in Neural Information Processing Systems, pp. 9916\u20139926 (2018)"},{"key":"2_CR32","unstructured":"Lee, X.Y., Havens, A., Chowdhary, G., Sarkar, S.: Learning to cope with adversarial attacks. arXiv preprint arXiv:1906.12061 (2019)"},{"key":"2_CR33","unstructured":"L\u00fctjens, B., Everett, M., How, J.P.: Certified adversarial robustness for deep reinforcement learning. arXiv preprint arXiv:1910.12908 (2019)"},{"key":"2_CR34","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"2_CR35","doi-asserted-by":"crossref","unstructured":"Dong, Y., et al.: Boosting adversarial attacks with momentum. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9185\u20139193 (2018)","DOI":"10.1109\/CVPR.2018.00957"},{"key":"2_CR36","unstructured":"Madry, A., Makelov, A., Schmidt, L., Tsipras, D., Vladu, A.: Towards deep learning models resistant to adversarial attacks. arXiv preprint arXiv:1706.06083 (2017)"}],"container-title":["Lecture Notes in Computer Science","Security, Privacy, and Anonymity in Computation, Communication, and Storage"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-68851-6_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,2,4]],"date-time":"2021-02-04T07:05:45Z","timestamp":1612422345000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-68851-6_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030688509","9783030688516"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-68851-6_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"5 February 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SpaCCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Security, Privacy and Anonymity in Computation, Communication and Storage","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Nanjing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 December 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 December 2020","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":"spaccs2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.spaccs2020.com\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"131","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":"48","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":"37% - 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":"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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}