IACR News item: 10 April 2023
EURECOM
Job Posting
The Digital Security Department of EURECOM, Sophia-Antipolis France, invites applications for a PhD position.
Topic - Artificial Intelligence (AI) technologies can efficiently process large amounts of data, to help stakeholders improve their services and propose applications tailored to end-user needs. While the benefits of AI technologies for the society are manifold and range from personalized services to improved healthcare, their adoption remains unfortunately slow due to various obstacles among which the lack of trustworthiness. Indeed, the performance and robustness of AI technologies rely on the access to large datasets of good quality. Such datasets usually include privacy-sensitive information. In this context, Federated learning (FL) is emerging as a powerful paradigm to collaboratively train a machine-learning (ML) model among thousands or even millions of participants. FL inherently promises (some) privacy and governance guarantees for the clients because the training data never leaves the client’s premises. Nevertheless, the collaborative aggregation of models’ parameters can potentially expose clients' specific information, and opens up to security breaches with potential loss of privacy. The successful candidate will study, the privacy and security challenges associated with federated learning and design and evaluate scalable and efficient privacy-enhancing technologies for FL using advanced cryptographic techniques such as multi-key homomorphic encryption or multi-party computation.
Requirements - Applicants should hold a Master degree or equivalent in Computer Science or a closely related area with a strong background on cryptography. Some background in machine learning is appreciated.
The application requires, among other documents, a CV, a cover letter describing the applicant’s research interests, the contact details of 2/3 persons that can provide references about the candidate and the transcripts of courses taken at graduate (and optionally undergraduate) level.
Topic - Artificial Intelligence (AI) technologies can efficiently process large amounts of data, to help stakeholders improve their services and propose applications tailored to end-user needs. While the benefits of AI technologies for the society are manifold and range from personalized services to improved healthcare, their adoption remains unfortunately slow due to various obstacles among which the lack of trustworthiness. Indeed, the performance and robustness of AI technologies rely on the access to large datasets of good quality. Such datasets usually include privacy-sensitive information. In this context, Federated learning (FL) is emerging as a powerful paradigm to collaboratively train a machine-learning (ML) model among thousands or even millions of participants. FL inherently promises (some) privacy and governance guarantees for the clients because the training data never leaves the client’s premises. Nevertheless, the collaborative aggregation of models’ parameters can potentially expose clients' specific information, and opens up to security breaches with potential loss of privacy. The successful candidate will study, the privacy and security challenges associated with federated learning and design and evaluate scalable and efficient privacy-enhancing technologies for FL using advanced cryptographic techniques such as multi-key homomorphic encryption or multi-party computation.
Requirements - Applicants should hold a Master degree or equivalent in Computer Science or a closely related area with a strong background on cryptography. Some background in machine learning is appreciated.
The application requires, among other documents, a CV, a cover letter describing the applicant’s research interests, the contact details of 2/3 persons that can provide references about the candidate and the transcripts of courses taken at graduate (and optionally undergraduate) level.
Closing date for applications:
Contact: Applicants are invited to send their applications via e-mail under reference [PhD-FLP] to melek.onen@eurecom.fr
Additional news items may be found on the IACR news page.