Mohamed Suliman
Hello! I am a 3rd year PhD student at Trinity College Dublin, The
University of Dublin. I work in the School of Computer Science and
Statistics on Machine Learning and Privacy (advised by Prof. Douglas
Leith), and I’m also a part of IBM Research. Contact me by sending
an email to sulimanm at tcd dot ie
News
- (June 2024) Talk: TechTalk #2 “Data Forging Is Harder Than You Think”
- (May 2024) New blog post Building and Training Neural Networks in Emacs Lisp
- (March 2024) Data Forging Is Harder Than You Think accepted in Privacy Regulation and Protection in Machine Learning Workshop at ICLR 2024
Publications & Pre-prints
- Towards a Re-evaluation of Data Forging Attacks in Practice. Mohamed Suliman, Anisa Halimi, Swanand Kadhe, Douglas Leith, Nathalie Baracaldo, Ambrish Rawat. (Pre-print)
- Securing Floating-Point Arithmetic for Noise Addition, Naoise Holohan, Stefano Braghin, Mohamed Suliman. ACM Annual Conference on Computer and Communications Security. CCS 2024.
- Data Forging Is Harder Than You Think, Mohamed Suliman, Swanand Kadhe, Anisa Halimi, Douglas Leith, Nathalie Baracaldo, Ambrish Rawat. Privacy Regulation and Protection in Machine Learning Workshop at ICLR 2024.
- Re-evaluating the Privacy Benefit of Federating Learning, Mohamed Suliman, Douglas Leith, Anisa Halimi. 1st Workshop on Advancements in Federated Learning at ECML-PKDD 2023.
- Two Models are Better than One: Federated Learning Is Not Private For Google GBoard Next Word Prediction, Mohamed Suliman, Douglas Leith. ESORICS 2023.
- Gradient information from Google GBoard NWP LSTM is Sufficient to Reconstruct Words Typed, Mohamed Suliman, Douglas Leith. CRCI 2022.