collaborators

5 papers

cs.CV2025

Defending Against Frequency-Based Attacks with Diffusion Models

Fatemeh Amerehi, Patrick Healy

Adversarial training is a common strategy for enhancing model robustness against adversarial attacks. However, it is typically tailored to the specific attack types it is trained o…

math.OC2025

Transforming Ridesharing: Harnessing Role Flexibility and HOV Integration for Enhanced Mobility Solutions

Fatemeh Amerehi, Patrick Healy

While dynamic ridesharing has been extensively studied, there remains a significant research gap in exploring role flexibility within the many-to-many ridesharing scheme, where the…

cs.CV2025

Narrowing Class-Wise Robustness Gaps in Adversarial Training

Fatemeh Amerehi, Patrick Healy

Efforts to address declining accuracy as a result of data shifts often involve various data-augmentation strategies. Adversarial training is one such method, designed to improve ro…

cs.CV2024

Label Augmentation for Neural Networks Robustness

Fatemeh Amerehi, Patrick Healy

Out-of-distribution generalization can be categorized into two types: common perturbations arising from natural variations in the real world and adversarial perturbations that are…

cs.LG2024

Interpretable Solutions for Breast Cancer Diagnosis with Grammatical Evolution and Data Augmentation

Yumnah Hasan, Allan de Lima, Fatemeh Amerehi +3

Medical imaging diagnosis increasingly relies on Machine Learning (ML) models. This is a task that is often hampered by severely imbalanced datasets, where positive cases can be qu…