Related papers: Compromising a Medical Mannequin
Machine learning models leak information about their training data every time they reveal a prediction. This is problematic when the training data needs to remain private. Private prediction methods limit how much information about the…
Machine Learning (ML) has revolutionized various domains, offering predictive capabilities in several areas. However, with the increasing accessibility of ML tools, many practitioners, lacking deep ML expertise, adopt a "push the button"…
Wearable devices, or "wearables," bring great benefits but also potential risks that could expose users' activities with- out their awareness or consent. In this paper, we report findings from the first large-scale survey conducted to…
Biometric systems involve security assurance to make our system highly secured and robust. Nowadays, biometric technology has been fixed into new systems with the aim of enforcing strong privacy and security. Several innovative system have…
Frontier AI systems are rapidly advancing in their capabilities to persuade, deceive, and influence human behaviour, with current models already demonstrating human-level persuasion and strategic deception in specific contexts. Humans are…
Advancements in AI capabilities, driven in large part by scaling up computing resources used for AI training, have created opportunities to address major global challenges but also pose risks of misuse. Hardware-enabled mechanisms (HEMs)…
Artificial Intelligence (AI) and Machine-Learning (ML) models have been increasingly used in medical products, such as medical device software. General considerations on the statistical aspects for the evaluation of AI/ML-enabled medical…
Today, computer systems hold large amounts of personal data. Yet while such an abundance of data allows breakthroughs in artificial intelligence, and especially machine learning (ML), its existence can be a threat to user privacy, and it…
It is important that consumers and regulators can verify the provenance of large neural models to evaluate their capabilities and risks. We introduce the concept of a "Proof-of-Training-Data": any protocol that allows a model trainer to…
A large body of research has shown that machine learning models are vulnerable to membership inference (MI) attacks that violate the privacy of the participants in the training data. Most MI research focuses on the case of a single…
Federated learning is a decentralized machine learning approach where clients train models locally and share model updates to develop a global model. This enables low-resource devices to collaboratively build a high-quality model without…
Physical adversarial attacks are increasingly studied in settings that resemble deployed surveillance systems rather than isolated image benchmarks. In these settings, person detection, multi-object tracking, visible--infrared sensing, and…
Machine learning has made remarkable advancements, but confidently utilising learning-enabled components in safety-critical domains still poses challenges. Among the challenges, it is known that a rigorous, yet practical, way of achieving…
Deep learning has attracted broad interest in healthcare and medical communities. However, there has been little research into the privacy issues created by deep networks trained for medical applications. Recently developed inference attack…
Recent studies have shown that distributed machine learning is vulnerable to gradient inversion attacks, where private training data can be reconstructed by analyzing the gradients of the models shared in training. Previous attacks…
Membership inference (MI) attack is currently the most popular test for measuring privacy leakage in machine learning models. Given a machine learning model, a data point and some auxiliary information, the goal of an MI attack is to…
This paper presents a mapping framework for design factors and implementation process for building credible Industrial Control Systems (ICS) security testbeds. The resilience of ICSs has become a critical concern to operators and…
Deploying machine learning models in production may allow adversaries to infer sensitive information about training data. There is a vast literature analyzing different types of inference risks, ranging from membership inference to…
The Internet of Medical Things (IoMT) is a frequent target of attacks -- compromising both patient data and healthcare infra-structure. While privacy-enhanced technologies and services (PETS) are developed to mitigate traditional privacy…
Industrial human-robot collaborative systems must be validated thoroughly with regard to safety. The sooner potential hazards for workers can be exposed, the less costly is the implementation of necessary changes. Due to the complexity of…