Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
110 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

On the Impact of Multi-dimensional Local Differential Privacy on Fairness (2312.04404v3)

Published 7 Dec 2023 in cs.LG, cs.CR, and cs.CY

Abstract: Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data as well as the resulting decisions, several ethical concerns need to be addressed for the appropriate use of such technologies, in particular, fairness and privacy. Unlike previous work, which focused on centralized differential privacy (DP) or local DP (LDP) for a single sensitive attribute, in this paper, we examine the impact of LDP in the presence of several sensitive attributes (i.e., multi-dimensional data) on fairness. Detailed empirical analysis on synthetic and benchmark datasets revealed very relevant observations. In particular, (1) multi-dimensional LDP is an efficient approach to reduce disparity, (2) the multi-dimensional approach of LDP (independent vs. combined) matters only at low privacy guarantees, and (3) the outcome Y distribution has an important effect on which group is more sensitive to the obfuscation. Last, we summarize our findings in the form of recommendations to guide practitioners in adopting effective privacy-preserving practices while maintaining fairness and utility in ML applications.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (45)
  1. Impact ldp on fairness repository. https://github.com/KarimaMakhlouf/Impact_of_LDP_on_Fairness.
  2. Survey on fairness notions and related tensions. arXiv preprint arXiv:2209.13012, 2022.
  3. Machine bias. propublica. See https://www. propublica. org/article/machine-bias-risk-assessments-in-criminal-sentencing, 2016.
  4. Differential Privacy Team Apple. Learning with privacy at scale, Dec 2017.
  5. Random sampling plus fake data: Multidimensional frequency estimates with local differential privacy. In Proceedings of the 30th ACM International Conference on Information & Knowledge Management, CIKM ’21, page 47–57, New York, NY, USA, 2021. Association for Computing Machinery.
  6. Multi-freq-ldpy: Multiple frequency estimation under local differential privacy in python. In Vijayalakshmi Atluri, Roberto Di Pietro, Christian D. Jensen, and Weizhi Meng, editors, Computer Security – ESORICS 2022, pages 770–775, Cham, 2022. Springer Nature Switzerland.
  7. (local) differential privacy has NO disparate impact on fairness. In Data and Applications Security and Privacy XXXVII, pages 3–21. Springer Nature Switzerland, 2023.
  8. Improving the utility of locally differentially private protocols for longitudinal and multidimensional frequency estimates. Digital Communications and Networks, 2022.
  9. Differential privacy has disparate impact on model accuracy. Advances in neural information processing systems, 32, 2019.
  10. Fairness and Machine Learning. fairmlbook.org, 2019. http://www.fairmlbook.org.
  11. Fairness in criminal justice risk assessments: The state of the art. Sociological Methods & Research, 50(1):3–44, 2021.
  12. Leo Breiman. Random forests. Machine learning, 45:5–32, 2001.
  13. On the privacy risks of algorithmic fairness. In 2021 IEEE European Symposium on Security and Privacy (EuroS&P), pages 292–303. IEEE, 2021.
  14. When fairness meets privacy: Fair classification with semi-private sensitive attributes. In Workshop on Trustworthy and Socially Responsible Machine Learning, NeurIPS 2022, 2022.
  15. Alexandra Chouldechova. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big data, 5(2):153–163, 2017.
  16. Algorithmic decision making and the cost of fairness. In Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pages 797–806, 2017.
  17. Felip: A local differentially private approach to frequency estimation on multidimensional datasets. In Proceedings of the 26th International Conference on Extending Database Technology, EDBT 2023, Ioannina, Greece, March 28 - March 31, 2023, pages 671–683. OpenProceedings.org, 2023.
  18. An empirical analysis of fairness notions under differential privacy. arXiv preprint arXiv:2302.02910, 2023.
  19. Retiring adult: New datasets for fair machine learning. Advances in Neural Information Processing Systems, 34, 2021.
  20. Multi-dimensional randomized response. IEEE Transactions on Knowledge and Data Engineering, 34(10):4933–4946, 2022.
  21. UCI machine learning repository, 2017.
  22. Fairness through awareness. In Proceedings of the 3rd innovations in theoretical computer science conference, pages 214–226, 2012.
  23. Calibrating noise to sensitivity in private data analysis. In Theory of Cryptography, pages 265–284. Springer Berlin Heidelberg, 2006.
  24. Rappor: Randomized aggregatable privacy-preserving ordinal response. In Proceedings of the 2014 ACM SIGSAC conference on computer and communications security, pages 1054–1067, 2014.
  25. Neither private nor fair: Impact of data imbalance on utility and fairness in differential privacy. In Proceedings of the 2020 Workshop on Privacy-Preserving Machine Learning in Practice, pages 15–19, 2020.
  26. Automated discovery of trade-off between utility, privacy and fairness in machine learning models. arXiv preprint arXiv:2311.15691, 2023.
  27. Differential privacy and fairness in decisions and learning tasks: A survey. arXiv preprint arXiv:2202.08187, 2022.
  28. Robin hood and matthew effects: Differential privacy has disparate impact on synthetic data. In International Conference on Machine Learning, pages 6944–6959. PMLR, 2022.
  29. Equality of opportunity in supervised learning. Advances in neural information processing systems, 29:3315–3323, 2016.
  30. Differentially private fair learning. In Kamalika Chaudhuri and Ruslan Salakhutdinov, editors, Proceedings of the 36th International Conference on Machine Learning, volume 97 of Proceedings of Machine Learning Research, pages 3000–3008. PMLR, 09–15 Jun 2019.
  31. Discrete distribution estimation under local privacy. In International Conference on Machine Learning, pages 2436–2444. PMLR, 2016.
  32. What can we learn privately? SIAM Journal on Computing, 40(3):793–826, 2011.
  33. Hiroaki Kikuchi. Castell: Scalable joint probability estimation of multi-dimensional data randomized with local differential privacy. arXiv preprint arXiv:2212.01627, 2022.
  34. Multi-dimensional data publishing with local differential privacy. In Proceedings of the 26th International Conference on Extending Database Technology, EDBT 2023, Ioannina, Greece, March 28 - March 31, 2023, pages 183–194. OpenProceedings.org, 2023.
  35. Machine learning fairness notions: Bridging the gap with real-world applications. Information Processing & Management, 58(5):102642, 2021.
  36. On the applicability of machine learning fairness notions. 23(1):14–23, may 2021.
  37. Differential privacy has bounded impact on fairness in classification. In Andreas Krause, Emma Brunskill, Kyunghyun Cho, Barbara Engelhardt, Sivan Sabato, and Jonathan Scarlett, editors, Proceedings of the 40th International Conference on Machine Learning, volume 202 of Proceedings of Machine Learning Research, pages 23681–23705. PMLR, 23–29 Jul 2023.
  38. A survey on bias and fairness in machine learning. ACM Comput. Surv., 54(6), jul 2021.
  39. Algorithmic fairness: Choices, assumptions, and definitions. Annual Review of Statistics and Its Application, 8:141–163, 2021.
  40. Fair learning with private demographic data. In International Conference on Machine Learning, pages 7066–7075. PMLR, 2020.
  41. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825–2830, 2011.
  42. Lopub: high-dimensional crowdsourced data publication with local differential privacy. IEEE Transactions on Information Forensics and Security, 13(9):2151–2166, 2018.
  43. Differentially private and fair deep learning: A lagrangian dual approach. Proceedings of the AAAI Conference on Artificial Intelligence, 35(11):9932–9939, May 2021.
  44. Fairness definitions explained. In 2018 IEEE/ACM International Workshop on Software Fairness (FairWare), pages 1–7. IEEE, 2018.
  45. Achieving differential privacy and fairness in logistic regression. In Companion proceedings of The 2019 world wide web conference, pages 594–599, 2019.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (5)
  1. Heber H. Arcolezi (15 papers)
  2. Sami Zhioua (10 papers)
  3. Ghassen Ben Brahim (3 papers)
  4. Catuscia Palamidessi (68 papers)
  5. karima Makhlouf (8 papers)
Citations (1)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets