Unsupervised multimodal deepfake detection using intra-and cross-modal inconsistencies

M Tian, M Khayatkhoei, J Mathai… - arxiv preprint arxiv …, 2023 - arxiv.org
Deepfake videos present an increasing threat to society with potentially negative impact on
criminal justice, democracy, and personal safety and privacy. Meanwhile, detecting …

A Critical Review of Predominant Bias in Neural Networks

J Li, M Khayatkhoei, J Zhu, H **e, ME Hussein… - arxiv preprint arxiv …, 2025 - arxiv.org
Bias issues of neural networks garner significant attention along with its promising
advancement. Among various bias issues, mitigating two predominant biases is crucial in …

SABAF: Removing strong attribute bias from neural networks with adversarial filtering

J Li, M Khayatkhoei, J Zhu, H **e, ME Hussein… - arxiv preprint arxiv …, 2023 - arxiv.org
Ensuring a neural network is not relying on protected attributes (eg, race, sex, age) for
prediction is crucial in advancing fair and trustworthy AI. While several promising methods …

Ethics and fairness for diabetes artificial intelligence

J Li, W Abd-Almageed - Diabetes Digital Health, Telehealth, and Artificial …, 2024 - Elsevier
Artificial intelligence (AI) has shown promising advances in diabetes care, particularly with
the use of neural networks for diagnosis and treatment. However, the utilization of AI without …