scispace - formally typeset
A

Ameer Mohammed

Researcher at Kuwait University

Publications -  23
Citations -  312

Ameer Mohammed is an academic researcher from Kuwait University. The author has contributed to research in topics: Obfuscation (software) & Encryption. The author has an hindex of 10, co-authored 22 publications receiving 206 citations. Previous affiliations of Ameer Mohammed include University of Virginia.

Papers
More filters
Journal ArticleDOI

Ensemble learning model for diagnosing COVID-19 from routine blood tests

TL;DR: The proposed ERLX is robust and can be deployed for reliable early and rapid screening of COVID-19 patients and revealed better performance when compared against existing state-of-the-art studies for the same set of features employed by them.
Book ChapterDOI

Lower Bounds on Assumptions Behind Indistinguishability Obfuscation

TL;DR: Barak et al. as mentioned in this paper proved lower bounds on the assumptions that imply indistinguishability obfuscation in a black-box way, based on computational assumptions, and they showed that achieving a fully blackbox construction of iO from exponentially secure collision-resistant hash functions unless the polynomial hierarchy collapses.
Proceedings Article

Universal Multi-Party Poisoning Attacks

TL;DR: In this article, the authors introduce and study a multi-party poisoning attack in which an adversary controls $k\in[m]$ of the parties, and for each corrupted party $P_i, the adversary submits some poisoned data on behalf of the correct party that is still ''$(1-p)$-close'' to the correct data.
Posted Content

More on Impossibility of Virtual Black-Box Obfuscation in Idealized Models.

TL;DR: Barak et al. as mentioned in this paper showed that general VBB obfuscation is not possible in idealized graded encoding models, assuming the existence of trapdoor permutations (TDPs).
Journal ArticleDOI

Deep forest model for diagnosing COVID-19 from routine blood tests.

TL;DR: A machine learning prediction model is proposed to accurately diagnose COVID-19 from clinical and/or routine laboratory data and exploits a new ensemble-based method called the deep forest (DF), where multiple classifiers in multiple layers are used to encourage diversity and improve performance.