Federated Learning (FL) enables the distributed training of a model across multiple data owners under the orchestration of a central server responsible for aggregating the models generated by the different clients. However, the original approach of FL has significant shortcomings related to privacy and fairness requirements. Specifically, the observation of the model updates may lead to privacy issues, such as membership inference attacks, while the use of imbalanced local datasets can introduce or amplify classification biases, especially for minority groups. In this work, we show that these biases can be exploited to increase the likelihood of privacy attacks against these groups. To do so, we propose a novel inference attack exploiting the knowledge of group fairness metrics during the training of the global model. Then to thwart this attack, we define a fairness-aware encrypted-domain aggregation algorithm that is differentially-private by design thanks to the approximate precision loss of the threshold multi-key CKKS homomorphic encryption scheme. Finally, we demonstrate the good performance of our proposal both in terms of fairness and privacy through experiments conducted over three real datasets.
----------------------------------------------------------------------
To follow the presentation remotely, please connect to the following URL with a modern web browser:
https://webinaire.numerique.gouv.fr/meeting/signin/invite/43499/creator/22714/hash/2504b153fb57548dd70dc97a77c3fe579bd445cb
----------------------------------------------------------------------
Seminar taking place in person with mandatory registration at least 48h beforehand for *all* in-person participants by email to Nadia Derouault nadia [*] derouault
inria [*] fr (<nadia[dot]derouault[at]inria[dot]fr>). Participants non-affiliated with Inria or IRISA will be asked to present an ID at the reception desk of the IRISA building.
To receive the SoSySec announcements, please subscribe to the SoSySec mailing list:
https://sympa.inria.fr/sympa/subscribe/sosysec
All past and future SoSySec talks are listed at
https://www.creachlabs.fr/en/seminars-keeping-date-latest-research/sosysec-seminar
----------------------------------------------------------------------
Séminaire en présentiel ouvert à tous mais avec inscription obligatoire au moins 48h à l'avance pour *tous* les participants en présentiel auprès de Nadia Derouault nadia [*] derouaultinria [*] fr (<nadia[dot]derouault[at]inria[dot]fr>).
Les participants externes devront se présenter à l'accueil avec une pièce d'identité.
Vous pouvez vous abonner à nos annonces de séminaires :
https://sympa.inria.fr/sympa/subscribe/sosysec
et consulter la liste des exposés passés et à venir :
https://www.creachlabs.fr/en/seminars-keeping-date-latest-research/sosysec-seminar