Related papers: Defending against adversarial attacks on medical i…
In practice, metric analysis on a specific train and test dataset does not guarantee reliable or fair ML models. This is partially due to the fact that obtaining a balanced, diverse, and perfectly labeled dataset is typically expensive,…
We address the problem of segmenting 3D multi-modal medical images in scenarios where very few labeled examples are available for training. Leveraging the recent success of adversarial learning for semi-supervised segmentation, we propose a…
Open-set recognition and adversarial defense study two key aspects of deep learning that are vital for real-world deployment. The objective of open-set recognition is to identify samples from open-set classes during testing, while…
Numerous safety- or security-critical systems depend on cameras to perceive their surroundings, further allowing artificial intelligence (AI) to analyze the captured images to make important decisions. However, a concerning attack vector…
Deep learning based methods for medical images can be easily compromised by adversarial examples (AEs), posing a great security flaw in clinical decision-making. It has been discovered that conventional adversarial attacks like PGD which…
Adversarial attacks are considered a potentially serious security threat for machine learning systems. Medical image analysis (MedIA) systems have recently been argued to be vulnerable to adversarial attacks due to strong financial…
We introduce a feature scattering-based adversarial training approach for improving model robustness against adversarial attacks. Conventional adversarial training approaches leverage a supervised scheme (either targeted or non-targeted) in…
The rapid and dynamic pace of Artificial Intelligence (AI) and Machine Learning (ML) is revolutionizing the insurance sector. AI offers significant, very much welcome advantages to insurance companies, and is fundamental to their…
In the rapidly evolving field of artificial intelligence, machine learning emerges as a key technology characterized by its vast potential and inherent risks. The stability and reliability of these models are important, as they are frequent…
We provide a comprehensive overview of adversarial machine learning focusing on two application domains, i.e., cybersecurity and computer vision. Research in adversarial machine learning addresses a significant threat to the wide…
Convolutional neural network-based medical image classifiers have been shown to be especially susceptible to adversarial examples. Such instabilities are likely to be unacceptable in the future of automated diagnoses. Though statistical…
Adversarial attacks and defenses in machine learning and deep neural network have been gaining significant attention due to the rapidly growing applications of deep learning in the Internet and relevant scenarios. This survey provides a…
Neural network-based approaches can achieve high accuracy in various medical image segmentation tasks. However, they generally require large labelled datasets for supervised learning. Acquiring and manually labelling a large medical dataset…
Deep neural networks are increasingly being used to detect and diagnose medical conditions using medical imaging. Despite their utility, these models are highly vulnerable to adversarial attacks and distribution shifts, which can affect…
Segmentation is considered to be a very crucial task in medical image analysis. This task has been easier since deep learning models have taken over with its high performing behavior. However, deep learning models dependency on large data…
Interpretation of medical images for diagnosis and treatment of complex disease from high-dimensional and heterogeneous data remains a key challenge in transforming healthcare. In the last few years, both supervised and unsupervised deep…
In this paper, we delve into the susceptibility of federated medical image analysis systems to adversarial attacks. Our analysis uncovers a novel exploitation avenue: using gradient information from prior global model updates, adversaries…
Adversarial training (AT) has been demonstrated as one of the most promising defense methods against various adversarial attacks. To our knowledge, existing AT-based methods usually train with the locally most adversarial perturbed points…
This paper investigates the critical issue of data poisoning attacks on AI models, a growing concern in the ever-evolving landscape of artificial intelligence and cybersecurity. As advanced technology systems become increasingly prevalent…
Deep learning models are being integrated into a wide range of high-impact, security-critical systems, from self-driving cars to medical diagnosis. However, recent research has demonstrated that many of these deep learning architectures are…