Related papers: Compromising a Medical Mannequin
Machine learning (ML) has established itself as a cornerstone for various critical applications ranging from autonomous driving to authentication systems. However, with this increasing adoption rate of machine learning models, multiple…
Machine Learning (ML) techniques have been rapidly adopted by smart Cyber-Physical Systems (CPS) and Internet-of-Things (IoT) due to their powerful decision-making capabilities. However, they are vulnerable to various security and…
Machine learning models were shown to be vulnerable to model stealing attacks, which lead to intellectual property infringement. Among other methods, substitute model training is an all-encompassing attack applicable to any machine learning…
Federated learning holds great potential for enabling large-scale healthcare research and collaboration across multiple centres while ensuring data privacy and security are not compromised. Although numerous recent studies suggest or…
Transfer learning has become a common solution to address training data scarcity in practice. It trains a specified student model by reusing or fine-tuning early layers of a well-trained teacher model that is usually publicly available.…
With the rise in the wholesale adoption of Deep Learning (DL) models in nearly all aspects of society, a unique set of challenges is imposed. Primarily centered around the architectures of these models, these risks pose a significant…
There is overwhelming evidence that the continued and widespread use of untested spreadsheets in business gives rise to regular, significant and unexpected financial losses. Whilst this is worrying, it is perhaps a relatively minor concern…
Modern machine learning (ML) models are expensive IP and business competitiveness often depends on keeping this IP confidential. This in turn restricts how these models are deployed; for example, it is unclear how to deploy a model…
As machine learning (ML) technologies and applications are rapidly changing many computing domains, security issues associated with ML are also emerging. In the domain of systems security, many endeavors have been made to ensure ML model…
Privacy concerns have led to the development of privacy-preserving approaches for learning models from sensitive data. Yet, in practice, even models learned with privacy guarantees can inadvertently memorize unique training examples or leak…
Different research communities have developed various approaches to assess the credibility of predictive models. Each approach usually works well for a specific type of model, and under some epistemic conditions that are normally satisfied…
The rapid adoption of deep learning in sensitive domains has brought tremendous benefits. However, this widespread adoption has also given rise to serious vulnerabilities, particularly model inversion (MI) attacks, posing a significant…
Machine learning (ML) is finding its way into safety-critical systems (SCS). Current safety standards and practice were not designed to cope with ML techniques, and it is difficult to be confident that SCSs that contain ML components are…
Deep neural networks have been shown to be vulnerable to backdoor attacks, which could be easily introduced to the training set prior to model training. Recent work has focused on investigating backdoor attacks on natural images or toy…
The success of machine learning is fueled by the increasing availability of computing power and large training datasets. The training data is used to learn new models or update existing ones, assuming that it is sufficiently representative…
Data leakage is the inadvertent transfer of information between training and evaluation datasets that poses a subtle, yet critical, risk to the reliability of machine learning (ML) models in safety-critical systems such as automotive…
Computing devices are vital to all areas of modern life and permeate every aspect of our society. The ubiquity of computing and our reliance on it has been accelerated and amplified by the COVID-19 pandemic. From education to work…
As the capabilities of large machine learning models continue to grow, and as the autonomy afforded to such models continues to expand, the spectre of a new adversary looms: the models themselves. The threat that a model might behave in a…
Machine learning can have major societal impact in computational biology applications. In particular, it plays a central role in the development of precision medicine, whereby treatment is tailored to the clinical or genetic features of the…
Due to hardware and software improvements, an increasing number of AI models are deployed on-device. This shift enhances privacy and reduces latency, but also introduces security risks distinct from traditional software. In this article, we…