Data-Driven Mitigation of Adversarial Text Perturbation

no code implementations • 19 Feb 2022 • Rasika Bhalerao, Mohammad Al-Rubaie, Anand Bhaskar, Igor Markov

We propose Continuous Word2Vec (CW2V), our data-driven method to learn word embeddings that ensures that perturbations of words have embeddings similar to those of the original words.

Adversarial Text Classification +2

Locally Differentially Private Naive Bayes Classification

no code implementations • 3 May 2019 • Emre Yilmaz, Mohammad Al-Rubaie, J. Morris Chang

In order to train a Naive Bayes classifier in an untrusted setting, we propose to use methods satisfying local differential privacy.

Classification Dimensionality Reduction +1

Privacy Preserving Machine Learning: Threats and Solutions

no code implementations • 27 Mar 2018 • Mohammad Al-Rubaie, J. Morris Chang

For privacy concerns to be addressed adequately in current machine learning systems, the knowledge gap between the machine learning and privacy communities must be bridged.

BIG-bench Machine Learning Privacy Preserving