84 citations · 140 across the 19 of their papers we have counts for
11 papers · 1 filter
MedISure: Towards Assuring Machine Learning-based Medical Image Classifiers using Mixup Boundary Analysis
Adam Byfield, William Poulett, Ben Wallace +6
Machine learning (ML) models are becoming integral in healthcare technologies, presenting a critical need for formal assurance to validate their safety, fairness, robustness, and t…
Multivessel Coronary Artery Segmentation and Stenosis Localisation using Ensemble Learning
Muhammad Bilal, Dinis Martinho, Reiner Sim +8
Coronary angiography analysis is a common clinical task performed by cardiologists to diagnose coronary artery disease (CAD) through an assessment of atherosclerotic plaque's accum…
Privacy Preserving Large Language Models: ChatGPT Case Study Based Vision and Framework
Imdad Ullah, Najm Hassan, Sukhpal Singh Gill +5
The generative Artificial Intelligence (AI) tools based on Large Language Models (LLMs) use billions of parameters to extensively analyse large datasets and extract critical privat…
Adversarial Machine Learning for Social Good: Reframing the Adversary as an Ally
Shawqi Al-Maliki, Adnan Qayyum, Hassan Ali +5
Deep Neural Networks (DNNs) have been the driving force behind many of the recent advances in machine learning. However, research has shown that DNNs are vulnerable to adversarial…
Privacy Preservation in Artificial Intelligence and Extended Reality (AI-XR) Metaverses: A Survey
Mahdi Alkaeed, Adnan Qayyum, Junaid Qadir
The metaverse is a nascent concept that envisions a virtual universe, a collaborative space where individuals can interact, create, and participate in a wide range of activities. P…
R2S100K: Road-Region Segmentation Dataset For Semi-Supervised Autonomous Driving in the Wild
Muhammad Atif Butt, Hassan Ali, Adnan Qayyum +3
Semantic understanding of roadways is a key enabling factor for safe autonomous driving. However, existing autonomous driving datasets provide well-structured urban roads while ign…
Membership Inference Attacks on DNNs using Adversarial Perturbations
Hassan Ali, Adnan Qayyum, Ala Al-Fuqaha +1
Several membership inference (MI) attacks have been proposed to audit a target DNN. Given a set of subjects, MI attacks tell which subjects the target DNN has seen during training.…
Robust Surgical Tools Detection in Endoscopic Videos with Noisy Data
Adnan Qayyum, Hassan Ali, Massimo Caputo +7
Over the past few years, surgical data science has attracted substantial interest from the machine learning (ML) community. Various studies have demonstrated the efficacy of emergi…
Lightweight Toxicity Detection in Spoken Language: A Transformer-based Approach for Edge Devices
Ahlam Husni Abu Nada, Siddique Latif, Junaid Qadir
Toxicity is a prevalent social behavior that involves the use of hate speech, offensive language, bullying, and abusive speech. While text-based approaches for toxicity detection a…
Can We Revitalize Interventional Healthcare with AI-XR Surgical Metaverses?
Adnan Qayyum, Muhammad Bilal, Muhammad Hadi +5
Recent advancements in technology, particularly in machine learning (ML), deep learning (DL), and the metaverse, offer great potential for revolutionizing surgical science. The com…
Consistent Valid Physically-Realizable Adversarial Attack against Crowd-flow Prediction Models
Hassan Ali, Muhammad Atif Butt, Fethi Filali +2
Recent works have shown that deep learning (DL) models can effectively learn city-wide crowd-flow patterns, which can be used for more effective urban planning and smart city manag…