PhD Project – Privacy and Fairness in Federated Learning for Digital Health (M/F)

Job title:

PhD Project – Privacy and Fairness in Federated Learning for Digital Health (M/F)

Company:

Job description

Offer DescriptionThe LIRIS laboratory is an internationally renowned research laboratory in the field of computer science and digital sciences. Located in Lyon, LIRIS stands out for its academic excellence and commitment to cutting-edge research. With a multidisciplinary team of passionate experts, the laboratory conducts innovative work covering a wide range of fields, such as artificial intelligence, computer vision, information systems, modeling and simulation, among others. With national and international collaborations, LIRIS offers a stimulating environment conducive to professional development, where innovative ideas and scientific advances are encouraged and valued. What we offer you:

• A stimulating working environment in contact with research staff
• 44 days of leave/RTT per year
• Excellent working conditions (flexible hours, etc.)
• Adapted training to support you • A site accessible by public transport
• Partial reimbursement of transport tickets (75%) + sustainable mobility package of up to €300/year

Summary:
Federated learning (FL) is a promising paradigm that is gaining grip in the context of privacy-preserving machine learning for edge computing systems. Thanks to FL, several data owners called clients (e.g., organizations in cross-silo FL) can collaboratively train a model on their private data, without having to send their raw data to external service providers. FL was rapidly adopted in several thriving applications such as digital healthcare [1], that is generating the world’s largest volume of data [2]. In healthcare systems, the problems of privacy and bias are particularly important.Although FL is a first step towards privacy by keeping the data local to each client, this is not sufficient since the model parameters shared by FL are vulnerable to privacy attack [3], as shown in a line of recent literature [4]. Thus, there is a need to design new FL protocols that are robust to such privacy attacks. Furthermore, FL clients may have very heterogeneous and imbalanced data, which may incur unfair FL model, with disparities among socioeconomic and demographic groups [6][4]. Recent studies show that the use of AI may further exacerbate disparities between groups, and that FL may be a vector of bias propagation among different FL client. In this context, recent works appeared in NDSS [7], and AAAI [8], show that fairness and privacy compete; handling them independently – as done usually – may have negative side-effects on each other.Therefore, there is a need for a novel multi-objective approach for FL fairness and protection against privacy threats. This is particularly challenging in FL where no global knowledge about statistical information of the overall heterogeneous data is available, a knowledge that is necessary in classical state-of-the-art techniques. This project tackles this challenge and aims to precisely handle the issues raised at the intersection of FL model privacy and fairness, through: (i) Novel distributed FL protocols; (ii) A multi-objective approach to take into account privacy, fairness and utility aspects, these objectives being antagonistic; (ii) Applying these techniques to FL-based digital health use cases.Keywords:
Distributed systems; Edge computing; Federated Learning; Privacy; Bias; Fairness; Healthcare dataReferences:
[1] N. Rieke, et. al. The Future of Digital Health with Federated Learning. NPJ Digital Medicine 3, 1, 2020.
[2] RBC. The Healthcare Data Explosion.
[3] R. Shokri, et al. Membership Inference Attacks Against Machine Learning Models. IEEE Symposium on Security and Privacy (S&P), May 2017.
[4] Z. Obermeyer, et al. Dissecting racial bias in an algorithm used to manage the health of populations. Science, 366(6464):447-453, Oct. 2019.
[5] N. A. Tomashenko, et. al. Privacy Attacks for Automatic Speech Recognition Acoustic Models in FL. ICASSP 2022.
[6] D. Leslie, et al. Does “AI” stand for augmenting inequality in the era of covid-19 healthcare? BMJ, 372:n304, Mar. 2021.
[7] M. Naseri, et al. Local and Central Differential Privacy for Robustness and Privacy in Federated Learning. NDSS 2022.
[8] H. Jeong, et al. Fairness without Imputation: A Decision Tree Approach for Fair Prediction with Missing Values. In the 36th AAAI Conference on Artificial Intelligence (AAAI), 2022.

Selected publications of the advisor related to the topic:

• C. Boscher, N. Benarba, F. Elhattab, S. Bouchenak. Personalized Privacy-Preserving Federated Learning. The 25th ACM/IFIP International Middleware Conference, Hong Kong, China, Dec. 2024. (Rank A)
• Y. Djebrouni, N. Benarba, O. Touat, S. Bouchenak, A. Bonifati, P. Da Rosa, P. Felber, V. Marangozova, V. Schiavoni. Bias Mitigation in Federated Learning for Edge Computing. The ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, UbiComp / IMWUT, 7(4), Melbourne, Australia, Oct. 2024. (Rank A*)
• F. Elhattab, C. Boscher, S. Bouchenak. PASTEL: Privacy-Preserving Federated Learning in Edge Computing. The ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, UbiComp / IMWUT, 7(4), Melbourne, Australia, Oct. 2024. (Rank A*)
• F. El Hattab, R. Talbi, V. Nitu, S. Bouchenak. Robust Federated Learning for Ubiquitous Computing Through Mitigation of Edge-Case Backdoor Attacks. The ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies, UbiComp / IMWUT, 6(4), Cancun, Mexico, Oct. 2023. (Rank A*)
• Z. Zhao, R. Birke, R. Han, B. Robu, S. Bouchenak, S. Ben Mokhtar, L. Chen. Enhancing Robustness of Online Learning Models on Highly Noisy Data. IEEE Transactions on Dependable and Secure Computing, 18(5), pp. 2177-2192, Sep. 2021. (Rank Q1)

Where to apply WebsiteRequirementsResearch Field Physics Education Level PhD or equivalentLanguages FRENCH Level BasicResearch Field Physics Years of Research Experience NoneAdditional InformationWebsite for additional job detailsWork Location(s)Number of offers available 1 Company/Institute Laboratoire d’informatique en image et systèmes d’information Country France City VILLEURBANNE GeofieldContact CityVILLEURBANNESTATUS: EXPIREDShare this page

Expected salary

Location

Villeurbanne, Rhône

Job date

Thu, 26 Dec 2024 08:48:24 GMT

To help us track our recruitment effort, please indicate in your email/cover letter where (vacanciesineu.com) you saw this job posting.