{"type":"ScholarlyArticle","title":"Post-processing of Differentially Private Data: A Fairness Perspective","authors":[{"name":"Keyu Zhu","slug":"keyu-zhu","given":"Keyu","family":"Zhu","affiliation":"Georgia Institute of Technology"},{"name":"Ferdinando Fioretto","slug":"ferdinando-fioretto","given":"Ferdinando","family":"Fioretto","affiliation":"Syracuse University"},{"name":"Pascal Van Hentenryck","slug":"pascal-van-hentenryck","given":"Pascal","family":"Van Hentenryck","affiliation":"Georgia Institute of Technology"}],"abstract":"Post-processing immunity is a fundamental property of differential privacy: it enables arbitrary data-independent transformations to differentially private outputs without affecting their privacy guarantees. Post-processing is routinely applied in data-release applications, including census data, which are then used to make allocations with substantial societal impacts. This paper shows that post-processing causes disparate impacts on individuals or groups and analyzes two critical settings: the release of differentially private datasets and the use of such private datasets for downstream decisions, such as the allocation of funds  informed by US Census data. In the first setting, the paper proposes tight bounds on the unfairness for traditional post-processing mechanisms, giving a unique tool to decision makers to quantify the disparate impacts introduced by their release. In the second setting, this paper proposes a novel post-processing mechanism that is (approximately) optimal under different fairness metrics, either reducing fairness issues substantially or reducing the cost of privacy. The theoretical analysis is complemented with numerical simulations on Census data.","doi":"10.24963/ijcai.2022/559","url":"https://ijcai.org/proceedings/2022/559","pdf":"https://ijcai.org/proceedings/2022/0559.pdf","markdown":"https://ijcai.org/proceedings/2022/559.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/559","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Multidisciplinary Topics and Applications","track":"Main Track","number":559,"pages":{"first":4029,"last":4035},"keywords":["AI Ethics, Trust, Fairness: Fairness & Diversity","Multidisciplinary Topics and Applications: Security and Privacy","Constraint Satisfaction and Optimization: Constraint Satisfaction","AI Ethics, Trust, Fairness: Bias"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986944","length_sec":82,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985087","length_sec":344,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Abowd and Schmutte, 2019] John M Abowd and Ian M Schmutte. An economic analysis of privacy protection and statistical accuracy as social choices. American Economic Review, 109(1):171-202, 2019.","title":"An economic analysis of privacy protection and statistical accuracy as social choices","authors":"M John, Ian M Abowd, Schmutte","year":"2019","venue":"American Economic Review","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Abowd et al., 2019] John Abowd, Robert Ashmead, Garfinkel Simson, Daniel Kifer, Philip Leclerc, Ashwin Machanavajjhala, and William Sexton. Census topdown: Differentially private data, incremental schemas, and consistency with public knowledge. US Census Bureau, 2019.","title":"Census topdown: Differentially private data, incremental schemas, and consistency with public knowledge","authors":"John Abowd, Robert Ashmead, Garfinkel Simson, Daniel Kifer, Philip Leclerc, Ashwin Machanavajjhala, William Sexton","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Abowd, 2018] John M Abowd. The US Census Bureau adopts differential privacy. In ACM SIGKDD Interna- tional Conference on Knowledge Discovery & Data Min- ing, pages 2867-2867. ACM, 2018.","title":"The US Census Bureau adopts differential privacy","authors":"John M Abowd","year":"2018","venue":"ACM SIGKDD International Conference on Knowledge Discovery & Data Mining","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cummings et al., 2019] Rachel Cummings, Varun Gupta, Dhamma Kimpara, and Jamie Morgenstern. On the com- patibility of privacy and fairness. In Proceedings of the Adjunct Publication of the 27th Conference on User Mod- eling, Adaptation and Personalization (UMAP), 2019.","title":"On the compatibility of privacy and fairness","authors":"Rachel Cummings, Varun Gupta, Dhamma Kimpara, Jamie Morgenstern","year":"2019","venue":"Proceedings of the Adjunct Publication of the 27th Conference on User Modeling, Adaptation and Personalization (UMAP)","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Dwork and Roth, 2013] Cynthia Dwork and Aaron Roth. The algorithmic foundations of differential privacy. Theo- retical Computer Science, 9(3-4):211-407, 2013.","title":"The algorithmic foundations of differential privacy","authors":"Roth ; Dwork, Cynthia Dwork, Aaron Roth","year":"2013","venue":"Theoretical Computer Science","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Dwork et al., 2006] Cynthia Dwork, Frank McSherry, Kobbi Nissim, and Adam Smith. Calibrating noise to sen- sitivity in private data analysis. In Theory of cryptography conference, pages 265-284. Springer, 2006.","title":"Calibrating noise to sensitivity in private data analysis","authors":"Cynthia Dwork, Frank Mcsherry, Kobbi Nissim, Adam Smith","year":"2006","venue":"Theory of cryptography conference","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Ekstrand et al., 2018] Michael D Ekstrand, Rezvan Joshaghani, and Hoda Mehrpouyan. Privacy for all: Ensuring fair and equitable privacy protections. In Proceedings of Conference on Fairness, Accountability and Transparency, pages 35-47, 2018.","title":"Privacy for all: Ensuring fair and equitable privacy protections","authors":"Rezvan Michael D Ekstrand, Hoda Joshaghani, Mehrpouyan","year":"2018","venue":"Proceedings of Conference on Fairness, Accountability and Transparency","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fioretto et al., 2018] Ferdinando Fioretto, Chansoo Lee, and Pascal Van Hentenryck. Constrained-based differen- tial privacy for private mobility. In Proceedings of the In- ternational Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS), pages 1405-1413, 2018.","title":"Constrained-based differential privacy for private mobility","authors":"Ferdinando Fioretto, Chansoo Lee, Pascal Van Hentenryck","year":"2018","venue":"Proceedings of the International Joint Conference on Autonomous Agents and Multiagent Systems (AAMAS)","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Fioretto et al., 2019] Ferdinando Fioretto, Terrence WK Mak, and Pascal Van Hentenryck. Differential privacy for power grid obfuscation. IEEE Transactions on Smart Grid, 11(2):1356-1366, 2019.","title":"Differential privacy for power grid obfuscation","authors":"Ferdinando Fioretto, Terrence Wk Mak, Pascal Van Hentenryck","year":"2019","venue":"IEEE Transactions on Smart Grid","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Jagielski et al., 2018] Matthew Jagielski, Michael Kearns, Jieming Mao, Alina Oprea, Aaron Roth, Saeed Sharifi- Malvajerdi, and Jonathan Ullman. Differentially private fair learning. arXiv preprint arXiv:1812.02696, 2018.","title":"Differentially private fair learning","authors":"Matthew Jagielski, Michael Kearns, Jieming Mao, Alina Oprea, Aaron Roth, Saeed Sharifi-Malvajerdi, Jonathan Ullman","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Pujol et al., 2020] David Pujol, Ryan McKenna, Satya Kup- pam, Michael Hay, Ashwin Machanavajjhala, and Gerome Miklau. Fair decision making using privacy-protected data. In Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, pages 189-199, 2020.","title":"Fair decision making using privacy-protected data","authors":"David Pujol, Ryan Mckenna, Satya Kuppam, Michael Hay, Ashwin Machanavajjhala, Gerome Miklau","year":"2020","venue":"Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Sonnenberg, 2016] W. Sonnenberg. Allocating grants for title i. U.S. Department of Education, Institute for Educa- tion Science, 2016.","title":"Allocating grants for title i","authors":"W Sonnenberg","year":"2016","venue":null,"doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Tran et al., 2021] Cuong Tran, Ferdinando Fioretto, Pas- cal Van Hentenryck, and Zhiyan Yao. Decision making with differential privacy under a fairness lens. In Zhi-Hua Zhou, editor, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event / Montreal, Canada, 19-27 August 2021, pages 560-566. ijcai.org, 2021.","title":"Decision making with differential privacy under a fairness lens","authors":"Cuong Tran, Ferdinando Fioretto, Pascal Van Hentenryck, Zhiyan Yao","year":"2021","venue":"Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Virtual Event","doi":null,"url":null,"internal_url":"/proceedings/2021/78"},{"position":14,"raw":"[Zhu et al., 2021] Keyu Zhu, Pascal Van Hentenryck, and Ferdinando Fioretto. Bias and variance of post-processing in differential privacy. In Proceedings of the AAAI Confer- ence on Artificial Intelligence, volume 35, pages 11177- 11184, 2021.","title":"Bias and variance of post-processing in differential privacy","authors":"Keyu Zhu, Pascal Van Hentenryck, Ferdinando Fioretto","year":"2021","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}