{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T12:51:54Z","timestamp":1756385514108},"reference-count":27,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,2]],"date-time":"2024-09-02T00:00:00Z","timestamp":1725235200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,2]]},"DOI":"10.1109\/csr61664.2024.10679438","type":"proceedings-article","created":{"date-parts":[[2024,9,24]],"date-time":"2024-09-24T17:21:51Z","timestamp":1727198511000},"page":"38-44","source":"Crossref","is-referenced-by-count":1,"title":["When Rewards Deceive: Counteracting Reward Poisoning on Online Deep Reinforcement Learning"],"prefix":"10.1109","author":[{"given":"Myria","family":"Bouhaddi","sequence":"first","affiliation":[{"name":"Computer Security Research Laboratory Université du Québec en Outaouais,Quebec,Canada"}]},{"given":"Kamel","family":"Adi","sequence":"additional","affiliation":[{"name":"Computer Security Research Laboratory Université du Québec en Outaouais,Quebec,Canada"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3543846"},{"key":"ref2","article-title":"Defense against reward poisoning attacks in reinforcement learning","author":"Banihashem","year":"2021","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Whatever does not kill deep rein-forcement learning, makes it stronger","author":"Behzadan","year":"2017","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CSR57506.2023.10224960"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126578"},{"key":"ref6","first-page":"1561","article-title":"Improved corruption robust algorithms for episodic reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref7","first-page":"1792","article-title":"Visualizing and understanding atari agents","volume-title":"International conference on machine learning","author":"Greydanus"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1002\/9781119861850.ch12"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2018.00057"},{"key":"ref10","article-title":"Actor-critic algorithms","author":"Konda","year":"1999","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Policy smoothing for provably robust reinforcement learning","author":"Kumar","year":"2021","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Policy poisoning in batch reinforcement learning and control","author":"Ma","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Playing atari with deep reinforcement learning","author":"Mnih","year":"2013","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref15","first-page":"7974","article-title":"Policy teaching via environment poisoning: Training-time adversarial attacks against reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Rakhsha"},{"key":"ref16","first-page":"8230","article-title":"Certified robustness to label-flipping attacks via randomized smoothing","volume-title":"International Conference on Machine Learning","author":"Rosenfeld"},{"key":"ref17","first-page":"1889","article-title":"Trust region policy optimization","volume-title":"International conference on machine learning","author":"Schulman"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1126\/science.aar6404"},{"journal-title":"Reinforcement learning: An introduction","year":"2018","author":"Sutton","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58951-6_24"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6086"},{"key":"ref22","article-title":"Copa: Certifying robust policies for offline reinforcement learning against poisoning attacks","author":"Wu","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26240"},{"key":"ref24","first-page":"5463","article-title":"Learning to explore via meta-policy gradient","volume-title":"International Conference on Machine Learning","author":"Xu"},{"key":"ref25","article-title":"Ro-bust reinforcement learning on state observations with learned optimal adversary","author":"Zhang","year":"2021","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487174"},{"key":"ref27","first-page":"11225","article-title":"Adaptive reward-poisoning attacks against reinforcement learning","volume-title":"International Conference on Machine Learning","author":"Zhang"}],"event":{"name":"2024 IEEE International Conference on Cyber Security and Resilience (CSR)","start":{"date-parts":[[2024,9,2]]},"location":"London, United Kingdom","end":{"date-parts":[[2024,9,4]]}},"container-title":["2024 IEEE International Conference on Cyber Security and Resilience (CSR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10679369\/10679342\/10679438.pdf?arnumber=10679438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,25]],"date-time":"2024-09-25T05:24:00Z","timestamp":1727241840000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10679438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,2]]},"references-count":27,"URL":"https:\/\/doi.org\/10.1109\/csr61664.2024.10679438","relation":{},"subject":[],"published":{"date-parts":[[2024,9,2]]}}}