Meta NYC
770 Broadway
New York City, NY 10003
About me

I am a Research Scientist at Meta in New York City.
My research interests are in the fields of machine learning, privacy and cloud security.

I received my BSc. and MSc. in Computer Engineering from University of Florence, then, in 2018, a PhD in Computer Science from University College London under the supervision of Prof. Emiliano De Cristofaro.
During my PhD, I spent a few months on research internships at INRIA in Grenoble, the Alan Turing Institute in London, and AWS AI in New York City.
My dissertation, titled ''Building and evaluating privacy-preserving data processing systems,'' can be found here.

  • Federated Linear Contextual Bandits with User-level Differential Privacy.
    Ruiquan Huang, Huanyu Zhang, Luca Melis, Milan Shen, Meisam Hejazinia, Jing Yang.
    In ICML 2023. [arXiv]
  • Federated Ensemble Learning: Increasing the Capacity of Label Private Recommendation Systems.
    Meisam Hejazinia, Dzmitry Huba, Ilias Leontiadis, Kiwan Maeng, Mani Malek, Luca Melis, Ilya Mironov, Milad Nasr, Kaikai Wang, Carole-Jean Wu.
    In IEEE Technical Committee on Data Engineering 2023. [arXiv]
  • Towards Fair Federated Recommendation Learning: Characterizing the Inter-Dependence of System and Data Heterogeneity.
    Kiwan Maeng, Haiyu Lu, Luca Melis, John Nguyen, Mike Rabbat, Carole-Jean Wu.
    In RecSys 2022. [arXiv]
  • Adversarial Robustness with Non-uniform Perturbations.
    Ecenaz Erdemir, Jeffrey Bickford, Luca Melis, Sergul Aydore.
    In NeurIPS 2021. [arXiv]
  • Differentially Private Query Release Through Adaptive Projection.
    Sergul Aydore, William Brown, Michael Kearns, Krishnaram Kenthapadi, Luca Melis, Aaron Roth.
    In ICML 2021. [arXiv]
  • Exploiting Unintended Feature Leakage in Collaborative Learning.
    Luca Melis, Congzheng Song, Emiliano De Cristofaro, Vitaly Shmatikov.
    In IEEE Symposium on Security & Privacy 2019. [arXiv]
  • On Collaborative Predictive Blacklisting.
    Luca Melis, Apostolos Pyrgelis, Emiliano De Cristofaro.
    In ACM SIGCOMM's Computer Communication Review (CCR) 2019. [arXiv]
  • LOGAN: Membership Inference Attacks Against Generative Models.
    Jamie Hayes, Luca Melis, George Danezis, Emiliano De Cristofaro.
    In the Proceedings on Privacy Enhancing Technologies (PoPETS), Vol. 2019, Issue 1. [arXiv]
  • Differentially Private Mixture of Generative Neural Networks.
    Gergely Acs, Luca Melis, Claude Castelluccia, Emiliano De Cristofaro.
    In IEEE International Conference on Data Mining (ICDM) 2017.
    Extended Version In IEEE Transactions on Knowledge and Data Engineering (TKDE) 2018. [ArXiv]
  • SplitBox: Toward Efficient Private Network Function Virtualization.
    Hassan Jameel Asghar, Luca Melis, Cyril Soldani, Emiliano De Cristofaro, Mohamed Ali Kaafar, Laurent Mathy.
    In ACM SIGCOMM Workshop on Hot Topics in Middleboxes and Network Function Virtualization, HotMiddlebox 2016. [ArXiv]
  • Private Processing of Outsourced Network Functions: Feasibility and Constructions.
    Luca Melis, Hassan Jameel Asghar, Emiliano De Cristofaro, Mohamed Ali Kaafar.
    In ACM Workshop on SDN-NFV Security 2016. [ArXiv]
       Best paper award! Invited for the NFV World Congress 2016