{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T12:20:34Z","timestamp":1783254034475,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":21,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,2,7]],"date-time":"2020-02-07T00:00:00Z","timestamp":1581033600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Google","award":["Research Award"],"award-info":[{"award-number":["Research Award"]}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation (NSF)","doi-asserted-by":"publisher","award":["CCF-1910769"],"award-info":[{"award-number":["CCF-1910769"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,2,7]]},"DOI":"10.1145\/3375627.3375833","type":"proceedings-article","created":{"date-parts":[[2020,2,5]],"date-time":"2020-02-05T01:10:22Z","timestamp":1580865022000},"page":"79-85","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":177,"title":["\"How do I fool you?\""],"prefix":"10.1145","author":[{"given":"Himabindu","family":"Lakkaraju","sequence":"first","affiliation":[{"name":"Harvard University, Cambridge, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Osbert","family":"Bastani","sequence":"additional","affiliation":[{"name":"University of Pennsylvania, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,2,7]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the International Conference on Very Large Data Bases (VLDB). 487--499","author":"Agrawal Rakesh","year":"2004","unstructured":"Rakesh Agrawal and Ramakrishnan Srikant. 2004. Fast algorithms for mining association rules. In Proceedings of the International Conference on Very Large Data Bases (VLDB). 487--499."},{"key":"e_1_3_2_1_2_1","volume-title":"Interpretability via model extraction. arXiv preprint arXiv:1706.09773","author":"Bastani Osbert","year":"2017","unstructured":"Osbert Bastani, Carolyn Kim, and Hamsa Bastani. 2017. Interpretability via model extraction. arXiv preprint arXiv:1706.09773 (2017)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","unstructured":"Rich Caruana Yin Lou Johannes Gehrke Paul Koch Marc Sturm and Noemie Elhadad. 2015. Intelligible Models for HealthCare: Predicting Pneumonia Risk and Hospital 30-day Readmission. In Knowledge Discovery and Data Mining (KDD) .","DOI":"10.1145\/2783258.2788613"},{"key":"e_1_3_2_1_4_1","volume-title":"Explanations can be manipulated and geometry is to blame. arXiv preprint arXiv:1906.07983","author":"Dombrowski Ann-Kathrin","year":"2019","unstructured":"Ann-Kathrin Dombrowski, Maximilian Alber, Christopher J Anders, Marcel Ackermann, Klaus-Robert M\u00fcller, and Pan Kessel. 2019. Explanations can be manipulated and geometry is to blame. arXiv preprint arXiv:1906.07983 (2019)."},{"key":"e_1_3_2_1_5_1","volume-title":"Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608","author":"Doshi-Velez Finale","year":"2017","unstructured":"Finale Doshi-Velez and Been Kim. 2017. Towards a rigorous science of interpretable machine learning. arXiv preprint arXiv:1702.08608 (2017)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013681"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/S0020-0190(99)00031-9"},{"key":"e_1_3_2_1_8_1","volume-title":"Learning Interpretable Models with Causal Guarantees. arXiv preprint arXiv:1901.08576","author":"Kim Carolyn","year":"2019","unstructured":"Carolyn Kim and Osbert Bastani. 2019. Learning Interpretable Models with Causal Guarantees. arXiv preprint arXiv:1901.08576 (2019)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.3386\/w23180"},{"key":"e_1_3_2_1_10_1","volume-title":"An evaluation of the human-interpretability of explanation. arXiv preprint arXiv:1902.00006","author":"Lage Isaac","year":"2019","unstructured":"Isaac Lage, Emily Chen, Jeffrey He, Menaka Narayanan, Been Kim, Sam Gershman, and Finale Doshi-Velez. 2019. An evaluation of the human-interpretability of explanation. arXiv preprint arXiv:1902.00006 (2019)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939874"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/3306618.3314229"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/1536414.1536459"},{"key":"e_1_3_2_1_14_1","volume-title":"Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model. Annals of Applied Statistics","author":"Letham Benjamin","year":"2015","unstructured":"Benjamin Letham, Cynthia Rudin, Tyler H. McCormick, and David Madigan. 2015. Interpretable classifiers using rules and Bayesian analysis: Building a better stroke prediction model. Annals of Applied Statistics (2015)."},{"key":"e_1_3_2_1_15_1","volume-title":"The mythos of model interpretability. arXiv preprint arXiv:1606.03490","author":"Lipton Zachary C","year":"2016","unstructured":"Zachary C Lipton. 2016. The mythos of model interpretability. arXiv preprint arXiv:1606.03490 (2016)."},{"key":"e_1_3_2_1_16_1","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems. 4765--4774."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Marco Tulio Ribeiro Sameer Singh and Carlos Guestrin. 2016. \"Why Should I Trust You?\": Explaining the Predictions of Any Classifier. In Knowledge Discovery and Data Mining (KDD) .","DOI":"10.18653\/v1\/N16-3020"},{"key":"e_1_3_2_1_18_1","volume-title":"Thirty-Second AAAI Conference on Artificial Intelligence .","author":"Ribeiro Marco Tulio","year":"2018","unstructured":"Marco Tulio Ribeiro, Sameer Singh, and Carlos Guestrin. 2018. Anchors: High-precision model-agnostic explanations. In Thirty-Second AAAI Conference on Artificial Intelligence ."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"e_1_3_2_1_20_1","first-page":"841","article-title":"Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GPDR","volume":"31","author":"Wachter Sandra","year":"2017","unstructured":"Sandra Wachter, Brent Mittelstadt, and Chris Russell. 2017. Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GPDR. Harv. JL & Tech. , Vol. 31 (2017), 841.","journal-title":"Harv. JL & Tech."},{"key":"e_1_3_2_1_21_1","volume-title":"Causal interpretations of black-box models. Journal of Business & Economic Statistics just-accepted","author":"Zhao Qingyuan","year":"2019","unstructured":"Qingyuan Zhao and Trevor Hastie. 2019. Causal interpretations of black-box models. Journal of Business & Economic Statistics just-accepted (2019), 1--19."}],"event":{"name":"AIES '20: AAAI\/ACM Conference on AI, Ethics, and Society","location":"New York NY USA","acronym":"AIES '20","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence"]},"container-title":["Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3375627.3375833","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3375627.3375833","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3375627.3375833","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:38:14Z","timestamp":1750199894000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3375627.3375833"}},"subtitle":["Manipulating User Trust via Misleading Black Box Explanations"],"short-title":[],"issued":{"date-parts":[[2020,2,7]]},"references-count":21,"alternative-id":["10.1145\/3375627.3375833","10.1145\/3375627"],"URL":"https:\/\/doi.org\/10.1145\/3375627.3375833","relation":{},"subject":[],"published":{"date-parts":[[2020,2,7]]},"assertion":[{"value":"2020-02-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}