{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T07:34:08Z","timestamp":1742974448471,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819986637"},{"type":"electronic","value":"9789819986644"}],"license":[{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,15]],"date-time":"2023-12-15T00:00:00Z","timestamp":1702598400000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8664-4_21","type":"book-chapter","created":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T06:05:13Z","timestamp":1702533913000},"page":"368-384","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cheat-FlipIt: An Approach to\u00a0Modeling and\u00a0Perception of\u00a0a\u00a0Deceptive Opponent"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2642-6865","authenticated-orcid":false,"given":"Qian","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9997-3747","authenticated-orcid":false,"given":"Xinli","family":"Xiong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,15]]},"reference":[{"key":"21_CR1","unstructured":"Bard, N., Johanson, M., Burch, N., Bowling, M.: Online implicit agent modelling. In: Proceedings of the 2013 International Conference on Autonomous Agents and Multi-Agent Systems, pp. 255\u2013262 (2013)"},{"issue":"6456","key":"21_CR2","doi-asserted-by":"publisher","first-page":"885","DOI":"10.1126\/science.aay2400","volume":"365","author":"N Brown","year":"2019","unstructured":"Brown, N., Sandholm, T.: Superhuman AI for multiplayer poker. Science 365(6456), 885\u2013890 (2019)","journal-title":"Science"},{"key":"21_CR3","unstructured":"Everett, R., Roberts, S.J.: Learning against non-stationary agents with opponent modelling and deep reinforcement learning. In: AAAI Spring Symposia (2018)"},{"key":"21_CR4","unstructured":"Foerster, J.N., Chen, R.Y., Al-Shedivat, M., Whiteson, S., Abbeel, P., Mordatch, I.: Learning with opponent-learning awareness. arXiv preprint arXiv:1709.04326 (2017)"},{"key":"21_CR5","unstructured":"Fortunato, M., et al.: Noisy networks for exploration. arXiv preprint arXiv:1706.10295 (2017)"},{"key":"21_CR6","unstructured":"Gleave, A., Dennis, M., Wild, C., Kant, N., Levine, S., Russell, S.: Adversarial policies: attacking deep reinforcement learning. arXiv preprint arXiv:1905.10615 (2019)"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Graves, A.: Long Short-Term Memory. Supervised Sequence Labelling with Recurrent Neural Networks, pp. 37\u201345 (2012)","DOI":"10.1007\/978-3-642-24797-2_4"},{"key":"21_CR8","series-title":"Studies in Computational Intelligence","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1007\/978-3-030-93409-5_68","volume-title":"Complex Networks & Their Applications X","author":"L Greige","year":"2022","unstructured":"Greige, L., Chin, P.: Deep reinforcement learning for FlipIt security game. In: Benito, R.M., Cherifi, C., Cherifi, H., Moro, E., Rocha, L.M., Sales-Pardo, M. (eds.) COMPLEX NETWORKS 2021. Studies in Computational Intelligence, vol. 1072, pp. 831\u2013843. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-030-93409-5_68"},{"key":"21_CR9","unstructured":"He, H., Boyd-Graber, J., Kwok, K., Daum\u00e9 III, H.: Opponent modeling in deep reinforcement learning. In: International Conference on Machine Learning, pp. 1804\u20131813. PMLR (2016)"},{"key":"21_CR10","unstructured":"Hong, Z.W., Su, S.Y., Shann, T.Y., Chang, Y.H., Lee, C.Y.: A deep policy inference q-network for multi-agent systems. arXiv preprint arXiv:1712.07893 (2017)"},{"key":"21_CR11","first-page":"1","volume":"53","author":"Y Hu","year":"2022","unstructured":"Hu, Y., Han, C., Li, H., Guo, T.: Modeling opponent learning in multiagent repeated games. Appl. Intell. 53, 1\u201317 (2022)","journal-title":"Appl. Intell."},{"key":"21_CR12","unstructured":"Kumar, A., Zhou, A., Tucker, G., Levine, S.: Conservative q-learning for offline reinforcement learning. In: Advances in Neural Information Processing Systems, vol. 33, pp. 1179\u20131191 (2020)"},{"issue":"12","key":"21_CR13","doi-asserted-by":"publisher","first-page":"7461","DOI":"10.1002\/int.22594","volume":"36","author":"Y Ma","year":"2021","unstructured":"Ma, Y., et al.: Opponent portrait for multiagent reinforcement learning in competitive environment. Int. J. Intell. Syst. 36(12), 7461\u20137474 (2021)","journal-title":"Int. J. Intell. Syst."},{"issue":"7540","key":"21_CR14","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":"21_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"364","DOI":"10.1007\/978-3-030-32430-8_22","volume-title":"Decision and Game Theory for Security","author":"L Oakley","year":"2019","unstructured":"Oakley, L., Oprea, A.: QFlip\u202f: an adaptive reinforcement learning strategy for the FlipIt security game. In: Alpcan, T., Vorobeychik, Y., Baras, J.S., D\u00e1n, G. (eds.) GameSec 2019. LNCS, vol. 11836, pp. 364\u2013384. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32430-8_22"},{"key":"21_CR16","unstructured":"Raileanu, R., Denton, E., Szlam, A., Fergus, R.: Modeling others using oneself in multi-agent reinforcement learning. In: International Conference on Machine Learning, pp. 4257\u20134266. PMLR (2018)"},{"key":"21_CR17","doi-asserted-by":"crossref","unstructured":"Shen, M., How, J.P.: Active perception in adversarial scenarios using maximum entropy deep reinforcement learning. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 3384\u20133390. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8794389"},{"issue":"7676","key":"21_CR18","doi-asserted-by":"publisher","first-page":"354","DOI":"10.1038\/nature24270","volume":"550","author":"D Silver","year":"2017","unstructured":"Silver, D., et al.: Mastering the game of go without human knowledge. Nature 550(7676), 354\u2013359 (2017)","journal-title":"Nature"},{"issue":"1","key":"21_CR19","first-page":"1929","volume":"15","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15(1), 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"21_CR20","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/TG.2020.3022698","volume":"15","author":"Z Tang","year":"2020","unstructured":"Tang, Z., Zhu, Y., Zhao, D., Lucas, S.M.: Enhanced rolling horizon evolution algorithm with opponent model learning. IEEE Trans. Games 15, 5\u201315 (2020)","journal-title":"IEEE Trans. Games"},{"key":"21_CR21","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1007\/s00145-012-9134-5","volume":"26","author":"M Van Dijk","year":"2013","unstructured":"Van Dijk, M., Juels, A., Oprea, A., Rivest, R.L.: Flipit: the game of \u201cstealthy takeover\u2019\u2019. J. Cryptol. 26, 655\u2013713 (2013)","journal-title":"J. Cryptol."},{"key":"21_CR22","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"},{"issue":"7782","key":"21_CR23","doi-asserted-by":"publisher","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","volume":"575","author":"O Vinyals","year":"2019","unstructured":"Vinyals, O., et al.: Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature 575(7782), 350\u2013354 (2019)","journal-title":"Nature"},{"key":"21_CR24","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)"},{"issue":"4","key":"21_CR25","doi-asserted-by":"publisher","first-page":"605","DOI":"10.3390\/e25040605","volume":"25","author":"Q Yao","year":"2023","unstructured":"Yao, Q., Wang, Y., Xiong, X., Wang, P., Li, Y.: Adversarial decision-making for moving target defense: a multi-agent Markov game and reinforcement learning approach. Entropy 25(4), 605 (2023)","journal-title":"Entropy"},{"key":"21_CR26","unstructured":"Zhang, C., Vinyals, O., Munos, R., Bengio, S.: A study on overfitting in deep reinforcement learning. arXiv preprint arXiv:1804.06893 (2018)"},{"issue":"10","key":"21_CR27","doi-asserted-by":"publisher","first-page":"202204","DOI":"10.1007\/s11432-021-3347-8","volume":"65","author":"J Zhu","year":"2022","unstructured":"Zhu, J., Wei, Y., Kang, Y., Jiang, X., Dullerud, G.E.: Adaptive deep reinforcement learning for non-stationary environments. Sci. China Inf. Sci. 65(10), 202204 (2022)","journal-title":"Sci. China Inf. Sci."}],"container-title":["Lecture Notes in Computer Science","Dependable Software Engineering. Theories, Tools, and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8664-4_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,14]],"date-time":"2023-12-14T06:09:43Z","timestamp":1702534183000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8664-4_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,15]]},"ISBN":["9789819986637","9789819986644"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8664-4_21","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,15]]},"assertion":[{"value":"15 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SETTA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Dependable Software Engineering: Theories, Tools, and Applications","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"setta2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/lcs.ios.ac.cn\/setta2023\/","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":"78","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":"24","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":"31% - 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":"7","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)"}}]}}