Search Results for author: Adel Elmahdy

Found 7 papers, 1 papers with code

Deconstructing Classifiers: Towards A Data Reconstruction Attack Against Text Classification Models

no code implementations23 Jun 2023 Adel Elmahdy, Ahmed Salem

In this work, we propose a new targeted data reconstruction attack called the Mix And Match attack, which takes advantage of the fact that most classification models are based on LLM.

Reconstruction Attack text-classification +1

Privacy Leakage in Text Classification: A Data Extraction Approach

no code implementations9 Jun 2022 Adel Elmahdy, Huseyin A. Inan, Robert Sim

Recent work has demonstrated the successful extraction of training data from generative language models.

Memorization text-classification +1

On the Fundamental Limits of Matrix Completion: Leveraging Hierarchical Similarity Graphs

no code implementations12 Sep 2021 Junhyung Ahn, Adel Elmahdy, Soheil Mohajer, Changho Suh

In the achievability proof, we demonstrate that probability of error of the maximum likelihood estimator vanishes for sufficiently large number of users and items, if all sufficient conditions are satisfied.

Matrix Completion Recommendation Systems +1

On the Fundamental Limits of Coded Data Shuffling for Distributed Machine Learning

no code implementations11 Jul 2018 Adel Elmahdy, Soheil Mohajer

In every shuffling iteration, each worker node processes a new subset of files, and has excess storage to partially cache the remaining files, assuming the cached files are uncoded.

BIG-bench Machine Learning

Active Learning for Top-$K$ Rank Aggregation from Noisy Comparisons

1 code implementation ICML 2017 Soheil Mohajer, Changho Suh, Adel Elmahdy

We explore an active top-$K$ ranking problem based on pairwise comparisons that are collected possibly in a sequential manner as per our design choice.

Active Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.