Short Bio

I am a PhD in privacy-preserving and robust Machine Learning. I did my PhD in the DRIM Research team at LIRIS laboratory from October 2018 to November 2021 under the supervision of Pr. Sara Bouchenak. The main focus of my thesis is Cryptography based Colaboratif Privacy Preserving Machine Learning and Robust Federated Learning.

Positon

I am working as an expert in privacy preserving artificial intelligence in Cygogn a french startup for automatic routing of B2B email traffic.

Publications

• Fatma-Zohra El Hattab, Rania Talbi, Vlad Nitu, Sara Bouchenak. ARMOR: Mitigating Poisoning Attacks in Federated Learning. The Network and Distributed System Security Symposium (NDSS), 2022 (under submission). (Rank A+)

• Rania Talbi, Sara Bouchenak. How Practical is Cryptography-Based Privacy Preserving Outsourced Machine Learning. The 40th International Symposium on Reliable Distributed Systems (SRDS), 2021 (under submission). (Rank A) Fatma-Zohra El Hattab,Rania Talbi, Sara Bouchenak, Vlad Nitu, and Sara BouchenakTowards Mitigating Poisoning Attacks in Federated Learning. Conférence francophone d'informatique en Parallélisme, Architecture et Système (ComPAS), 2021.

• Rania Talbi. Towards Practical Privacy-Preserving Collaborative Machine Learning at a Scale. The Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) - Doctoral Forum, 2020. (Rank A)

• Jiyue Huang, Rania Talbi, Zilong Zhao, Sara Bouchenak, Lydia Y. Chen, Stefanie Roos. An Exploratory Analysis on Users’ Contributions in Federated Learning. IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications (TPS-ISA), 2020

• Fatma-Zohra El Hattab,Rania Talbi, Sara Bouchenak, and Vlad Nitu. How Effective Are DataPoisoning Attacks on FederatedLearning. Conférence francophone d'informatique en Parallélisme, Architecture et Système (ComPAS), 2020.

• Nassim Ait Ali Braham, Rania Talbi, Sara Bouchenak. PrivML: Practical End-to-End Privacy Preserving Online Machine Learning. Conférence francophone d'informatique en Parallélisme, Architecture et Système (ComPAS), 2019.

• Rania Talbi, Sara Bouchenak, Lydia Y. Chen. Towards Dynamic End-to-End Privacy Preserving Data Classification. The Annual IEEE/IFIP International Conference on Dependable Systems and Networks (DSN) - Fast Abstract, 2018. (Rank A)

• Rémi Canillas, Rania Talbi, Sara Bouchenak, Omar Hasan, Lionel Brunie, Laurent Sarrat: Exploratory Study of Privacy Preserving Fraud Detection. The annual ACM/IFIP Middleware conference, 2018. (Rank A)