{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:58:41Z","timestamp":1777658321639,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":54,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"NUS Early Career Research Award","award":["NUS ECRAFY19 P16"],"award-info":[{"award-number":["NUS ECRAFY19 P16"]}]},{"name":"Singapore Ministry of Education Academic Research Fund","award":["R-252-000- 660-133"],"award-info":[{"award-number":["R-252-000- 660-133"]}]},{"name":"National Research Foundation, Singapore","award":["AISG-RP-2018-009"],"award-info":[{"award-number":["AISG-RP-2018-009"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,21]]},"DOI":"10.1145\/3461702.3462533","type":"proceedings-article","created":{"date-parts":[[2021,7,31]],"date-time":"2021-07-31T01:21:38Z","timestamp":1627694498000},"page":"231-241","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":73,"title":["On the Privacy Risks of Model Explanations"],"prefix":"10.1145","author":[{"given":"Reza","family":"Shokri","sequence":"first","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"given":"Martin","family":"Strobel","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}]},{"given":"Yair","family":"Zick","sequence":"additional","affiliation":[{"name":"University of Massachusetts, Amherst, Amherst, MA, USA"}]}],"member":"320","published-online":{"date-parts":[[2021,7,30]]},"reference":[{"key":"e_1_3_2_2_1_1","volume-title":"Proceedings of the 23rd ACM SIGSAC Conference on Computer and Communications Security (CCS), 308--318","author":"Abadi M.","unstructured":"abadi2016deep Abadi , M. ; Chu , A. ; Goodfellow , I. ; McMahan , H. B. ; Mironov , I. ; Talwar , K. ; and Zhang , L . 2016. Deep learning with differential privacy . In Proceedings of the 23rd ACM SIGSAC Conference on Computer and Communications Security (CCS), 308--318 . abadi2016deepAbadi, M.; Chu, A.; Goodfellow, I.; McMahan, H. B.; Mironov, I.; Talwar, K.; and Zhang, L. 2016. Deep learning with differential privacy. In Proceedings of the 23rd ACM SIGSAC Conference on Computer and Communications Security (CCS), 308--318."},{"key":"e_1_3_2_2_2_1","first-page":"95","article-title":"uditingAdler, P.; Falk, C.; Friedler, S. A.; Rybeck, G.; Scheidegger, C.; Smith, B.; and Venkatasubramanian, S. 2018. Auditing black-box models for indirect influence","volume":"54","year":"2016","unstructured":"adler 2016 a uditingAdler, P.; Falk, C.; Friedler, S. A.; Rybeck, G.; Scheidegger, C.; Smith, B.; and Venkatasubramanian, S. 2018. Auditing black-box models for indirect influence . Knowledge and Information Systems 54 : 95 -- 122 . adler2016auditingAdler, P.; Falk, C.; Friedler, S. A.; Rybeck, G.; Scheidegger, C.; Smith, B.; and Venkatasubramanian, S. 2018. Auditing black-box models for indirect influence. Knowledge and Information Systems 54: 95--122.","journal-title":"Knowledge and Information Systems"},{"key":"e_1_3_2_2_3_1","unstructured":"dji Bolot and Gambs(2020)]aivodji2020modelA\u00efvodji U.; Bolot A.; and Gambs S. 2020. Model extraction from counterfactual explanations.  dji Bolot and Gambs(2020)]aivodji2020modelA\u00efvodji U.; Bolot A.; and Gambs S. 2020. Model extraction from counterfactual explanations."},{"key":"e_1_3_2_2_4_1","volume-title":"Montavon, Samek, M\u00fc ller, D\"a hne, and Kindermans]Alber2018Alber, M.","year":"2018","unstructured":"ele , Sch\u00fc tt , Montavon, Samek, M\u00fc ller, D\"a hne, and Kindermans]Alber2018Alber, M. ; Lapuschkin, S .; Seegerer, P.; H\"a gele, M.; Sch\u00fc tt, K. T.; Montavon, G.; Samek, W.; M\u00fc ller, K.; D\"a hne, S.; and Kindermans, P. 2018 . iNNvestigate neural networks! arXiv preprint arXiv:1808.04260 . ele, Sch\u00fc tt, Montavon, Samek, M\u00fc ller, D\"a hne, and Kindermans]Alber2018Alber, M.; Lapuschkin, S.; Seegerer, P.; H\"a gele, M.; Sch\u00fc tt, K. T.; Montavon, G.; Samek, W.; M\u00fc ller, K.; D\"a hne, S.; and Kindermans, P. 2018. iNNvestigate neural networks! arXiv preprint arXiv:1808.04260 ."},{"key":"e_1_3_2_2_5_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR), 1--16","author":"Gross","unstructured":"tireli, and Gross ]Ancona2017Ancona, M.; Ceolini , E. ; \u00d6 ztireli, C.; and Gross , M . 2018. Towards better understanding of gradient-based attribution methods for Deep Neural Networks . In Proceedings of the 6th International Conference on Learning Representations (ICLR), 1--16 . tireli, and Gross]Ancona2017Ancona, M.; Ceolini, E.; \u00d6 ztireli, C.; and Gross, M. 2018. Towards better understanding of gradient-based attribution methods for Deep Neural Networks. In Proceedings of the 6th International Conference on Learning Representations (ICLR), 1--16."},{"key":"e_1_3_2_2_6_1","volume-title":"Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 169--191.","author":"Gross","year":"2019","unstructured":"tireli, and Gross ]ancona2017dnnsAncona, M.; Ceolini , E. ; \u00d6 ztireli, C.; and Gross , M . 2019 . Gradient-Based Attribution Method . In Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 169--191. tireli, and Gross]ancona2017dnnsAncona, M.; Ceolini, E.; \u00d6 ztireli, C.; and Gross, M. 2019. Gradient-Based Attribution Method. In Explainable AI: Interpreting, Explaining and Visualizing Deep Learning, 169--191."},{"key":"e_1_3_2_2_7_1","first-page":"1803","article-title":"Baehrens, D.; Schroeter, T.; Harmeling, S.; Kawanabe, M.; Hansen, K.; and Mueller, K. 2009. How to Explain Individual Classification Decisions","volume":"11","author":"Baehrens","year":"2009","unstructured":"Baehrens 2009 Baehrens, D.; Schroeter, T.; Harmeling, S.; Kawanabe, M.; Hansen, K.; and Mueller, K. 2009. How to Explain Individual Classification Decisions . Journal of Machine Learning Research 11 : 1803 -- 1831 . Baehrens2009Baehrens, D.; Schroeter, T.; Harmeling, S.; Kawanabe, M.; Hansen, K.; and Mueller, K. 2009. How to Explain Individual Classification Decisions. Journal of Machine Learning Research 11: 1803--1831.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_2_8_1","volume-title":"The Right to Information and Privacy: Balancing Rights and Managing Conflicts","author":"Banisar D.","unstructured":"banisar2011 Banisar , D. 2011. The Right to Information and Privacy: Balancing Rights and Managing Conflicts . World Bank Institute Governance Working Paper prefixhttps:\/\/ssrn.com\/abstract=1786473. banisar2011Banisar, D. 2011. The Right to Information and Privacy: Balancing Rights and Managing Conflicts. World Bank Institute Governance Working Paper prefixhttps:\/\/ssrn.com\/abstract=1786473."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"crossref","unstructured":"belkin2003laplacianBelkin M.; and Niyogi P. 2003. Laplacian eigenmaps for dimensionality reduction and data representation. Neural computation 15(6): 1373--1396.  belkin2003laplacianBelkin M.; and Niyogi P. 2003. Laplacian eigenmaps for dimensionality reduction and data representation. Neural computation 15(6): 1373--1396.","DOI":"10.1162\/089976603321780317"},{"key":"e_1_3_2_2_10_1","volume-title":"Proceedings of the 17th Annual Conference on Neural Information Processing Systems (NIPS), 985--992","author":"Brand M.","year":"2003","unstructured":"brand2003charting Brand , M. 2003 . Charting a manifold . In Proceedings of the 17th Annual Conference on Neural Information Processing Systems (NIPS), 985--992 . brand2003chartingBrand, M. 2003. Charting a manifold. In Proceedings of the 17th Annual Conference on Neural Information Processing Systems (NIPS), 985--992."},{"key":"e_1_3_2_2_11_1","unstructured":"Carlini2018Carlini N.; Liu C.; Kos J.; Erlingsson \u00da .; and Song D. 2018. The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets. arXiv preprint arXiv:1802.08232 .  Carlini2018Carlini N.; Liu C.; Kos J.; Erlingsson \u00da .; and Song D. 2018. The Secret Sharer: Measuring Unintended Neural Network Memorization & Extracting Secrets. arXiv preprint arXiv:1802.08232 ."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"crossref","unstructured":"009)]daligault2009Daligault J.; and Thomass\u00e9 S. 2009. On Finding Directed Trees with Many Leaves. In Parameterized and Exact Computation 86--97.  009)]daligault2009Daligault J.; and Thomass\u00e9 S. 2009. On Finding Directed Trees with Many Leaves. In Parameterized and Exact Computation 86--97.","DOI":"10.1007\/978-3-642-11269-0_7"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI), 511--517","author":"Datta","unstructured":"Datta 2015influenceDatta, A.; Datta , A. ; Procaccia , A. D. ; and Zick , Y . 2015. Influence in Classification via Cooperative Game Theory . In Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI), 511--517 . Datta2015influenceDatta, A.; Datta, A.; Procaccia, A. D.; and Zick, Y. 2015. Influence in Classification via Cooperative Game Theory. In Proceedings of the 24th International Joint Conference on Artificial Intelligence (IJCAI), 511--517."},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the 24th ACM SIGSAC Conference on Computer and Communications Security (CCS), 1193--1210","author":"Datta A.","unstructured":"datta2017programs Datta , A. ; Fredrikson , M. ; Ko , G. ; Mardziel , P. ; and Sen , S . 2017. Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs . In Proceedings of the 24th ACM SIGSAC Conference on Computer and Communications Security (CCS), 1193--1210 . datta2017programsDatta, A.; Fredrikson, M.; Ko, G.; Mardziel, P.; and Sen, S. 2017. Use Privacy in Data-Driven Systems: Theory and Experiments with Machine Learnt Programs. In Proceedings of the 24th ACM SIGSAC Conference on Computer and Communications Security (CCS), 1193--1210."},{"key":"e_1_3_2_2_15_1","volume-title":"Proceedings of the 37th IEEE Conference on Security and Privacy (Oakland), 598--617","author":"Datta","unstructured":"Datta 2016Datta, A.; Sen , S. ; and Zick , Y . 2016. Transparency via Quantitative Input Influence . In Proceedings of the 37th IEEE Conference on Security and Privacy (Oakland), 598--617 . Datta2016Datta, A.; Sen, S.; and Zick, Y. 2016. Transparency via Quantitative Input Influence. In Proceedings of the 37th IEEE Conference on Security and Privacy (Oakland), 598--617."},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"crossref","unstructured":"de2008snpingde Souza N. 2008. SNPing away at anonymity. nature methods 5(11): 918--918.  de2008snpingde Souza N. 2008. SNPing away at anonymity. nature methods 5(11): 918--918.","DOI":"10.1038\/nmeth1108-918a"},{"key":"e_1_3_2_2_17_1","unstructured":"Dua2017Dua D.; and Graff C. 2017. UCI Machine Learning Repository. prefixhttp:\/\/archive.ics.uci.edu\/ml.  Dua2017Dua D.; and Graff C. 2017. UCI Machine Learning Repository. prefixhttp:\/\/archive.ics.uci.edu\/ml."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-statistics-060116-054123"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1090\/jams\/852"},{"key":"e_1_3_2_2_20_1","unstructured":"gilmer2018adversarialGilmer J.; Metz L.; Faghri F.; Schoenholz S. S.; Raghu M.; Wattenberg M.; and Goodfellow I. 2018. Adversarial Spheres. arXiv preprint arXiv:1801.02774 .  gilmer2018adversarialGilmer J.; Metz L.; Faghri F.; Schoenholz S. S.; Raghu M.; Wattenberg M.; and Goodfellow I. 2018. Adversarial Spheres. arXiv preprint arXiv:1801.02774 ."},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v38i3.2741"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"crossref","unstructured":"homer2008resolvingHomer N.; Szelinger S.; Redman M.; Duggan D.; Tembe W.; Muehling J.; Pearson J. V.; Stephan D. A.; Nelson S. F.; and Craig D. W. 2008. Resolving individuals contributing trace amounts of DNA to highly complex mixtures using high-density SNP genotyping microarrays. PLoS Genet 4(8): e1000167.  homer2008resolvingHomer N.; Szelinger S.; Redman M.; Duggan D.; Tembe W.; Muehling J.; Pearson J. V.; Stephan D. A.; Nelson S. F.; and Craig D. W. 2008. Resolving individuals contributing trace amounts of DNA to highly complex mixtures using high-density SNP genotyping microarrays. PLoS Genet 4(8): e1000167.","DOI":"10.1371\/journal.pgen.1000167"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376219"},{"key":"e_1_3_2_2_24_1","unstructured":"ler Binder Montavon Samek and Bach]Klauschen2015Klauschen F.; M\u00fc ller K.; Binder A.; Montavon G.; Samek W.; and Bach S. 2015. On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation. Plos One .  ler Binder Montavon Samek and Bach]Klauschen2015Klauschen F.; M\u00fc ller K.; Binder A.; Montavon G.; Samek W.; and Bach S. 2015. On Pixel-Wise Explanations for Non-Linear Classifier Decisions by Layer-Wise Relevance Propagation. Plos One ."},{"key":"e_1_3_2_2_25_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML)","author":"Koh P. W.","unstructured":"koh2017understanding Koh , P. W. ; and Liang , P . 2017. Understanding Black-box Predictions via Influence Functions . In Proceedings of the 34th International Conference on Machine Learning (ICML) , 1885--1894. koh2017understandingKoh, P. W.; and Liang, P. 2017. Understanding Black-box Predictions via Influence Functions. In Proceedings of the 34th International Conference on Machine Learning (ICML), 1885--1894."},{"key":"e_1_3_2_2_26_1","unstructured":"krizhevsky2009learningKrizhevsky A.; and Hinton G. 2009. Learning multiple layers of features from tiny images. Technical report.  krizhevsky2009learningKrizhevsky A.; and Hinton G. 2009. Learning multiple layers of features from tiny images. Technical report."},{"key":"e_1_3_2_2_27_1","volume-title":"Proceedings of the 26th Annual Conference on Neural Information Processing Systems (NIPS), 1097--1105","author":"Krizhevsky A.","unstructured":"krizhevsky2012imagenet Krizhevsky , A. ; Sutskever , I. ; and Hinton , G. E . 2012. Imagenet classification with deep convolutional neural networks . In Proceedings of the 26th Annual Conference on Neural Information Processing Systems (NIPS), 1097--1105 . krizhevsky2012imagenetKrizhevsky, A.; Sutskever, I.; and Hinton, G. E. 2012. Imagenet classification with deep convolutional neural networks. In Proceedings of the 26th Annual Conference on Neural Information Processing Systems (NIPS), 1097--1105."},{"key":"e_1_3_2_2_28_1","unstructured":"kumar2020problemsKumar I. E.; Venkatasubramanian S.; Scheidegger C.; and Friedler S. 2020. Problems with Shapley-value-based explanations as feature importance measures. arXiv preprint arXiv:2002.11097 .  kumar2020problemsKumar I. E.; Venkatasubramanian S.; Scheidegger C.; and Friedler S. 2020. Problems with Shapley-value-based explanations as feature importance measures. arXiv preprint arXiv:2002.11097 ."},{"key":"e_1_3_2_2_29_1","unstructured":"long2017towardsLong Y.; Bindschaedler V.; and Gunter C. A. 2017. Towards measuring membership privacy. arXiv preprint arXiv:1712.09136 .  long2017towardsLong Y.; Bindschaedler V.; and Gunter C. A. 2017. Towards measuring membership privacy. arXiv preprint arXiv:1712.09136 ."},{"key":"e_1_3_2_2_30_1","volume-title":"Proceedings of the 1st ACM Conference on Fairness, Accountability, and Transparency (ACM FAT*), 1--9.","author":"Milli","unstructured":"Milli 2018Milli, S.; Schmidt , L. ; Dragan , A. D. ; and Hardt , M . 2019. Model Reconstruction from Model Explanations . In Proceedings of the 1st ACM Conference on Fairness, Accountability, and Transparency (ACM FAT*), 1--9. Milli2018Milli, S.; Schmidt, L.; Dragan, A. D.; and Hardt, M. 2019. Model Reconstruction from Model Explanations. In Proceedings of the 1st ACM Conference on Fairness, Accountability, and Transparency (ACM FAT*), 1--9."},{"key":"e_1_3_2_2_31_1","volume-title":"Proceedings of the 24th Annual Conference on Neural Information Processing Systems (NIPS), 1786--1794","author":"leNarayanan H.","unstructured":"narayanan2010samp leNarayanan , H. ; and Mitter , S . 2010. Sample complexity of testing the manifold hypothesis . In Proceedings of the 24th Annual Conference on Neural Information Processing Systems (NIPS), 1786--1794 . narayanan2010sampleNarayanan, H.; and Mitter, S. 2010. Sample complexity of testing the manifold hypothesis. In Proceedings of the 24th Annual Conference on Neural Information Processing Systems (NIPS), 1786--1794."},{"key":"e_1_3_2_2_32_1","volume-title":"Proceedings of the 25th ACM SIGSAC Conference on Computer and Communications Security (CCS), 634--646","author":"Nasr","unstructured":"Nasr 2018Nasr, M.; Shokri , R. ; and Houmansadr , A . 2018. Machine Learning with Membership Privacy using Adversarial Regularization . In Proceedings of the 25th ACM SIGSAC Conference on Computer and Communications Security (CCS), 634--646 . Nasr2018Nasr, M.; Shokri, R.; and Houmansadr, A. 2018. Machine Learning with Membership Privacy using Adversarial Regularization. In Proceedings of the 25th ACM SIGSAC Conference on Computer and Communications Security (CCS), 634--646."},{"key":"e_1_3_2_2_33_1","unstructured":"commissionerGuidance2020Office I. C. 2020. Guidance on the AI auditing framework Draft guidance for consultation. prefixhttps:\/\/ico.org.uk\/media\/about-the-ico\/consultations\/2617219\/guidance-on-the-ai-auditing-framework-draft-for-consultation.pdf.  commissionerGuidance2020Office I. C. 2020. Guidance on the AI auditing framework Draft guidance for consultation. prefixhttps:\/\/ico.org.uk\/media\/about-the-ico\/consultations\/2617219\/guidance-on-the-ai-auditing-framework-draft-for-consultation.pdf."},{"key":"e_1_3_2_2_34_1","volume-title":"Proceedings of the 6th International Conference on Learning Representations (ICLR), 1--34","author":"Papernot","year":"2018","unstructured":"Papernot 2018aPapernot, N.; Song , S. ; Mironov , I. ; Raghunathan , A. ; Talwar , K. ; and Erlingsson , \u00da. 2018 . Scalable Private Learning with PATE . In Proceedings of the 6th International Conference on Learning Representations (ICLR), 1--34 . Papernot2018aPapernot, N.; Song, S.; Mironov, I.; Raghunathan, A.; Talwar, K.; and Erlingsson, \u00da. 2018. Scalable Private Learning with PATE. In Proceedings of the 6th International Conference on Learning Representations (ICLR), 1--34."},{"key":"e_1_3_2_2_35_1","volume-title":"H.","author":"Petitcolas F.","unstructured":"petitcolas2011kerckhoffs Petitcolas , F. 2011. Kerckhoffs' Principle. In van Tilborg , H. ; and S., J., eds., Encyclopedia of Cryptography and Security . petitcolas2011kerckhoffsPetitcolas, F. 2011. Kerckhoffs' Principle. In van Tilborg, H.; and S., J., eds., Encyclopedia of Cryptography and Security."},{"key":"e_1_3_2_2_36_1","volume-title":"Proceedings of the 22nd International Conference on Knowledge Discovery and Data Mining (KDD), 1135--1144","author":"Ribeiro","unstructured":"Ribeiro 2016shouldRibeiro, M. T.; Singh , S. ; and Guestrin , C . 2016. Why Should I Trust You?: Explaining the Predictions of Any Classifier . In Proceedings of the 22nd International Conference on Knowledge Discovery and Data Mining (KDD), 1135--1144 . Ribeiro2016shouldRibeiro, M. T.; Singh, S.; and Guestrin, C. 2016. Why Should I Trust You?: Explaining the Predictions of Any Classifier. In Proceedings of the 22nd International Conference on Knowledge Discovery and Data Mining (KDD), 1135--1144."},{"key":"e_1_3_2_2_37_1","volume-title":"Anchors: High-Precision Model-Agnostic Explanations. In AAAI Conference on Artificial Intelligence. prefixhttps:\/\/homes.cs.washington.edu\/simmarcotcr\/aaai18","author":"Ribeiro","unstructured":"Ribeiro 2018Ribeiro, M. T.; Singh , S. ; and Guestrin , C . 2018 . Anchors: High-Precision Model-Agnostic Explanations. In AAAI Conference on Artificial Intelligence. prefixhttps:\/\/homes.cs.washington.edu\/simmarcotcr\/aaai18 .pdf. Ribeiro2018Ribeiro, M. T.; Singh, S.; and Guestrin, C. 2018. Anchors: High-Precision Model-Agnostic Explanations. In AAAI Conference on Artificial Intelligence. prefixhttps:\/\/homes.cs.washington.edu\/simmarcotcr\/aaai18.pdf."},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_2_39_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML), 5558--5567","author":"Sablayrolles A.","unstructured":"u]sablayrolles2019white Sablayrolles , A. ; Douze , M. ; Ollivier , Y. ; Schmid , C. ; and J\u00e9gou , H . 2019. White-box vs Black-box: Bayes Optimal Strategies for Membership Inference . In Proceedings of the 36th International Conference on Machine Learning (ICML), 5558--5567 . u]sablayrolles2019whiteSablayrolles, A.; Douze, M.; Ollivier, Y.; Schmid, C.; and J\u00e9gou, H. 2019. White-box vs Black-box: Bayes Optimal Strategies for Membership Inference. In Proceedings of the 36th International Conference on Machine Learning (ICML), 5558--5567."},{"key":"e_1_3_2_2_40_1","volume-title":"Proceedings - IEEE Symposium on Security and Privacy 3--18","author":"Shokri","unstructured":"Shokri , Stronati, Song , and Shmatikov]Shokri2017aShokri, R.; Stronati , M. ; Song , C. ; and Shmatikov , V . 2017 a . Membership Inference Attacks Against Machine Learning Models . Proceedings - IEEE Symposium on Security and Privacy 3--18 . Shokri, Stronati, Song, and Shmatikov]Shokri2017aShokri, R.; Stronati, M.; Song, C.; and Shmatikov, V. 2017 a . Membership Inference Attacks Against Machine Learning Models. Proceedings - IEEE Symposium on Security and Privacy 3--18."},{"key":"e_1_3_2_2_41_1","volume-title":"Proceedings of the 38th IEEE Conference on Security and Privacy (Oakland), 3--18","author":"Shokri","unstructured":"Shokri , Stronati, Song , and Shmatikov]Shokri2017Shokri, R.; Stronati , M. ; Song , C. ; and Shmatikov , V . 2017 b . Membership Inference Attacks Against Machine Learning Models . In Proceedings of the 38th IEEE Conference on Security and Privacy (Oakland), 3--18 . Shokri, Stronati, Song, and Shmatikov]Shokri2017Shokri, R.; Stronati, M.; Song, C.; and Shmatikov, V. 2017 b . Membership Inference Attacks Against Machine Learning Models. In Proceedings of the 38th IEEE Conference on Security and Privacy (Oakland), 3--18."},{"key":"e_1_3_2_2_42_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML), 3145--3153","author":"Shrikumar A.","unstructured":"]shrikumar2017deeplift Shrikumar , A. ; Greenside , P. ; and Kundaje , A . 2017 a . Learning Important Features Through Propagating Activation Differences . In Proceedings of the 34th International Conference on Machine Learning (ICML), 3145--3153 . ]shrikumar2017deepliftShrikumar, A.; Greenside, P.; and Kundaje, A. 2017 a . Learning Important Features Through Propagating Activation Differences. In Proceedings of the 34th International Conference on Machine Learning (ICML), 3145--3153."},{"key":"e_1_3_2_2_43_1","unstructured":"]Shrikumar2017Shrikumar A.; Greenside P.; and Kundaje A. 2017 b . Not just a black box: Learning Important Features Through Propagating Activation Differences. arXiv preprint arXiv:1605.01713 .  ]Shrikumar2017Shrikumar A.; Greenside P.; and Kundaje A. 2017 b . Not just a black box: Learning Important Features Through Propagating Activation Differences. arXiv preprint arXiv:1605.01713 ."},{"key":"e_1_3_2_2_44_1","unstructured":"Simonyan2013aSimonyan K.; Vedaldi A.; and Zisserman A. 2013. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. arXiv preprint arXiv:1312.6034 .  Simonyan2013aSimonyan K.; Vedaldi A.; and Zisserman A. 2013. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. arXiv preprint arXiv:1312.6034 ."},{"key":"e_1_3_2_2_45_1","unstructured":"ribeiro2016programsSingh S.; Ribeiro M. T.; and Guestrin C. 2016. Programs as Black-Box Explanations. arXiv preprint arXiv:1611.07579 .  ribeiro2016programsSingh S.; Ribeiro M. T.; and Guestrin C. 2016. Programs as Black-Box Explanations. arXiv preprint arXiv:1611.07579 ."},{"key":"e_1_3_2_2_46_1","volume-title":"Proceedings of the 3rd AAAI\/ACM Conference on AI, Ethics, and Society (AIES), 180--186","author":"Slack D.","unstructured":"slack2020fooling Slack , D. ; Hilgard , S. ; Jia , E. ; Singh , S. ; and Lakkaraju , H . 2020. Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods . In Proceedings of the 3rd AAAI\/ACM Conference on AI, Ethics, and Society (AIES), 180--186 . slack2020foolingSlack, D.; Hilgard, S.; Jia, E.; Singh, S.; and Lakkaraju, H. 2020. Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methods. In Proceedings of the 3rd AAAI\/ACM Conference on AI, Ethics, and Society (AIES), 180--186."},{"key":"e_1_3_2_2_47_1","volume-title":"Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), 718--725","author":"Sliwinski","unstructured":"Sliwinski 2019Sliwinski, J.; Strobel , M. ; and Zick , Y . 2019. Axiomatic Characterization of Data-Driven Influence Measures for Classification . In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), 718--725 . Sliwinski2019Sliwinski, J.; Strobel, M.; and Zick, Y. 2019. Axiomatic Characterization of Data-Driven Influence Measures for Classification. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), 718--725."},{"key":"e_1_3_2_2_48_1","unstructured":"Smilkov2017Smilkov D.; Thorat N.; Kim B.; Viegas F.; and Winterberg M. 2017. SmoothGrad : removing noise by adding noise. arXiv preprint arXiv:1706.03825 .  Smilkov2017Smilkov D.; Thorat N.; Kim B.; Viegas F.; and Winterberg M. 2017. SmoothGrad : removing noise by adding noise. arXiv preprint arXiv:1706.03825 ."},{"key":"e_1_3_2_2_49_1","volume-title":"Proceedings of the 26th ACM SIGSAC Conference on Computer and Communications Security (CCS), 241--257","author":"Song L.","unstructured":"song2019privacy Song , L. ; Shokri , R. ; and Mittal , P . 2019. Privacy risks of securing machine learning models against adversarial examples . In Proceedings of the 26th ACM SIGSAC Conference on Computer and Communications Security (CCS), 241--257 . song2019privacySong, L.; Shokri, R.; and Mittal, P. 2019. Privacy risks of securing machine learning models against adversarial examples. In Proceedings of the 26th ACM SIGSAC Conference on Computer and Communications Security (CCS), 241--257."},{"key":"e_1_3_2_2_50_1","unstructured":"Springenberg2014Springenberg J. T.; Dosovitskiy A.; Brox T.; and Riedmiller M. 2014. Striving for Simplicity: The All Convolutional Net. arXiv preprint arXiv:1412.6806 .  Springenberg2014Springenberg J. T.; Dosovitskiy A.; Brox T.; and Riedmiller M. 2014. Striving for Simplicity: The All Convolutional Net. arXiv preprint arXiv:1412.6806 ."},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"crossref","unstructured":"Strack2014Strack B.; Deshazo J. P.; Gennings C.; Olmo J. L.; Ventura S.; Cios K. J.; and Clore J. N. 2014. Impact of HbA1c measurement on hospital readmission rates: Analysis of 70 000 clinical database patient records. BioMed Research International 2014.  Strack2014Strack B.; Deshazo J. P.; Gennings C.; Olmo J. L.; Ventura S.; Cios K. J.; and Clore J. N. 2014. Impact of HbA1c measurement on hospital readmission rates: Analysis of 70 000 clinical database patient records. BioMed Research International 2014.","DOI":"10.1155\/2014\/781670"},{"key":"e_1_3_2_2_52_1","unstructured":"sundararajan2019shapleySundararajan M.; and Najmi A. 2019. The many Shapley values for model explanation. arXiv preprint arXiv:1908.08474 .  sundararajan2019shapleySundararajan M.; and Najmi A. 2019. The many Shapley values for model explanation. arXiv preprint arXiv:1908.08474 ."},{"key":"e_1_3_2_2_53_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML), 3319--3328","author":"Sundararajan M.","unstructured":"sundararajan2017axiomatic Sundararajan , M. ; Taly , A. ; and Yan , Q . 2017. Axiomatic Attribution for Deep Networks . In Proceedings of the 34th International Conference on Machine Learning (ICML), 3319--3328 . sundararajan2017axiomaticSundararajan, M.; Taly, A.; and Yan, Q. 2017. Axiomatic Attribution for Deep Networks. In Proceedings of the 34th International Conference on Machine Learning (ICML), 3319--3328."},{"key":"e_1_3_2_2_54_1","volume-title":"2018 IEEE 31st Computer Security Foundations Symposium (CSF), 268--282","author":"Yeom","unstructured":"t al.(2018) Yeom , Giacomelli, Fredrikson , and Jha ]Yeom2017Yeom, S.; Giacomelli , I. ; Fredrikson , M. ; and Jha , S . 2018. Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting . In 2018 IEEE 31st Computer Security Foundations Symposium (CSF), 268--282 . t al.(2018)Yeom, Giacomelli, Fredrikson, and Jha ]Yeom2017Yeom, S.; Giacomelli, I.; Fredrikson, M.; and Jha, S. 2018. Privacy Risk in Machine Learning: Analyzing the Connection to Overfitting. In 2018 IEEE 31st Computer Security Foundations Symposium (CSF), 268--282."}],"event":{"name":"AIES '21: AAAI\/ACM Conference on AI, Ethics, and Society","location":"Virtual Event USA","acronym":"AIES '21","sponsor":["SIGAI ACM Special Interest Group on Artificial Intelligence","AAAI"]},"container-title":["Proceedings of the 2021 AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3461702.3462533","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3461702.3462533","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:49:06Z","timestamp":1750193346000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3461702.3462533"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,21]]},"references-count":54,"alternative-id":["10.1145\/3461702.3462533","10.1145\/3461702"],"URL":"https:\/\/doi.org\/10.1145\/3461702.3462533","relation":{},"subject":[],"published":{"date-parts":[[2021,7,21]]},"assertion":[{"value":"2021-07-30","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}