Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning

Lea Demelius

doi:10.1609/aaai.v39i28.35205

Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning

Lea Demelius^*

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Abstract

Developing trustworthy AI requires advancing methods that meet key requirements such as privacy or fairness while maintaining strong utility, as well as understanding the intricate interdependencies between these dimensions, which often manifest as trade-offs. My PhD research focuses on differential privacy, which is widely regarded as the state-of-the-art for protecting privacy in data analysis and machine learning. I investigate the relationships between differential privacy, utility and fairness, with the goal of advancing the adoption of differentially private machine learning in real-world settings.

Original language	English
Title of host publication	IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and Demonstrations
Editors	Toby Walsh, Julie Shah, Zico Kolter
Publisher	Association for the Advancement of Artificial Intelligence (AAAI)
Pages	29255-29256
Number of pages	2
Volume	39
Edition	28
ISBN (Electronic)	157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 157735897X, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978, 9781577358978
DOIs	https://doi.org/10.1609/aaai.v39i28.35205
Publication status	Published - 11 Apr 2025
Event	39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025 - Philadelphia, United States Duration: 25 Feb 2025 → 4 Mar 2025 https://aaai.org/conference/aaai/aaai-25/

Publication series

Name	Proceedings of the AAAI Conference on Artificial Intelligence
Number	28
Volume	39
ISSN (Print)	2159-5399
ISSN (Electronic)	2374-3468

Conference

Conference	39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025
Abbreviated title	AAAI 2025
Country/Territory	United States
City	Philadelphia
Period	25/02/25 → 4/03/25
Internet address	https://aaai.org/conference/aaai/aaai-25/

ASJC Scopus subject areas

Artificial Intelligence

Access to Document

10.1609/aaai.v39i28.35205

Cite this

Demelius, L. (2025). Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning. In T. Walsh, J. Shah, & Z. Kolter (Eds.), IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and Demonstrations (28 ed., Vol. 39, pp. 29255-29256). (Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 39, No. 28). Association for the Advancement of Artificial Intelligence (AAAI) . https://doi.org/10.1609/aaai.v39i28.35205

Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning. / Demelius, Lea.
IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and Demonstrations. ed. / Toby Walsh; Julie Shah; Zico Kolter. Vol. 39 28. ed. Association for the Advancement of Artificial Intelligence (AAAI) , 2025. p. 29255-29256 (Proceedings of the AAAI Conference on Artificial Intelligence; Vol. 39, No. 28).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Demelius, L 2025, Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning. in T Walsh, J Shah & Z Kolter (eds), IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and Demonstrations. 28 edn, vol. 39, Proceedings of the AAAI Conference on Artificial Intelligence, no. 28, vol. 39, Association for the Advancement of Artificial Intelligence (AAAI) , pp. 29255-29256, 39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025, Philadelphia, United States, 25/02/25. https://doi.org/10.1609/aaai.v39i28.35205

Demelius L. Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning. In Walsh T, Shah J, Kolter Z, editors, IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and Demonstrations. 28 ed. Vol. 39. Association for the Advancement of Artificial Intelligence (AAAI) . 2025. p. 29255-29256. (Proceedings of the AAAI Conference on Artificial Intelligence; 28). doi: 10.1609/aaai.v39i28.35205

Demelius, Lea. / Privacy, Utility and Fairness : Navigating Trade-offs in Differentially Private Machine Learning. IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and Demonstrations. editor / Toby Walsh ; Julie Shah ; Zico Kolter. Vol. 39 28. ed. Association for the Advancement of Artificial Intelligence (AAAI) , 2025. pp. 29255-29256 (Proceedings of the AAAI Conference on Artificial Intelligence; 28).

@inproceedings{b71c5a4e79be41149edc824b787127b9,

title = "Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning",

abstract = "Developing trustworthy AI requires advancing methods that meet key requirements such as privacy or fairness while maintaining strong utility, as well as understanding the intricate interdependencies between these dimensions, which often manifest as trade-offs. My PhD research focuses on differential privacy, which is widely regarded as the state-of-the-art for protecting privacy in data analysis and machine learning. I investigate the relationships between differential privacy, utility and fairness, with the goal of advancing the adoption of differentially private machine learning in real-world settings.",

author = "Lea Demelius",

note = "Publisher Copyright: Copyright {\textcopyright} 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.; 39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025, AAAI 2025 ; Conference date: 25-02-2025 Through 04-03-2025",

year = "2025",

month = apr,

day = "11",

doi = "10.1609/aaai.v39i28.35205",

language = "English",

volume = "39",

series = "Proceedings of the AAAI Conference on Artificial Intelligence",

publisher = "Association for the Advancement of Artificial Intelligence (AAAI) ",

number = "28",

pages = "29255--29256",

editor = "Toby Walsh and Julie Shah and Zico Kolter",

booktitle = "IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and Demonstrations",

edition = "28",

url = "https://aaai.org/conference/aaai/aaai-25/",

}

TY - GEN

T1 - Privacy, Utility and Fairness

T2 - 39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

AU - Demelius, Lea

PY - 2025/4/11

Y1 - 2025/4/11

N2 - Developing trustworthy AI requires advancing methods that meet key requirements such as privacy or fairness while maintaining strong utility, as well as understanding the intricate interdependencies between these dimensions, which often manifest as trade-offs. My PhD research focuses on differential privacy, which is widely regarded as the state-of-the-art for protecting privacy in data analysis and machine learning. I investigate the relationships between differential privacy, utility and fairness, with the goal of advancing the adoption of differentially private machine learning in real-world settings.

AB - Developing trustworthy AI requires advancing methods that meet key requirements such as privacy or fairness while maintaining strong utility, as well as understanding the intricate interdependencies between these dimensions, which often manifest as trade-offs. My PhD research focuses on differential privacy, which is widely regarded as the state-of-the-art for protecting privacy in data analysis and machine learning. I investigate the relationships between differential privacy, utility and fairness, with the goal of advancing the adoption of differentially private machine learning in real-world settings.

UR - http://www.scopus.com/inward/record.url?scp=105003906449&partnerID=8YFLogxK

U2 - 10.1609/aaai.v39i28.35205

DO - 10.1609/aaai.v39i28.35205

M3 - Conference paper

AN - SCOPUS:105003906449

VL - 39

T3 - Proceedings of the AAAI Conference on Artificial Intelligence

SP - 29255

EP - 29256

BT - IAAI-25, EAAI-25, AAAI-25 Student Abstracts, Undergraduate Consortium and Demonstrations

A2 - Walsh, Toby

A2 - Shah, Julie

A2 - Kolter, Zico

PB - Association for the Advancement of Artificial Intelligence (AAAI)

Y2 - 25 February 2025 through 4 March 2025

ER -

Privacy, Utility and Fairness: Navigating Trade-offs in Differentially Private Machine Learning

Abstract

Publication series

Conference

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this