Related papers: Improving TBI Protection Measures and Standards fo…
Deep models, while being extremely versatile and accurate, are vulnerable to adversarial attacks: slight perturbations that are imperceptible to humans can completely flip the prediction of deep models. Many attack and defense mechanisms…
Reactive defense mechanisms, such as intrusion detection systems, have made significant efforts to secure a system or network for the last several decades. However, the nature of reactive security mechanisms has limitations because…
The increasing complexity of modern robotic systems and the environments they operate in necessitates the formal consideration of safety in the presence of imperfect measurements. In this paper we propose a rigorous framework for…
Poisoning attacks can disproportionately influence model behaviour by making small changes to the training corpus. While defences against specific poisoning attacks do exist, they in general do not provide any guarantees, leaving them…
Recent years have witnessed a boom of connected medical devices, which brings security issues in the meantime. Medical imaging devices, an essential part of medical cyber-physical systems, play a vital role in modern hospitals and are often…
Objective: Head impact information including impact directions, speeds and force are important to study traumatic brain injury, design and evaluate protective gears. This study presents a deep learning model developed to accurately predict…
In the field of Image Quality Assessment (IQA), the adversarial robustness of the metrics poses a critical concern. This paper presents a comprehensive benchmarking study of various defense mechanisms in response to the rise in adversarial…
This paper studies the problem of defending (1D and 2D) boundaries against a large number of continuous attacks with a heterogeneous group of defenders. The defender team has perfect information of the attack events within some time (finite…
How can we make machine learning provably robust against adversarial examples in a scalable way? Since certified defense methods, which ensure $\epsilon$-robust, consume huge resources, they can only achieve small degree of robustness in…
Stochastic optimization problems often involve the expectation in its objective. When risk is incorporated in the problem description as well, then risk measures have to be involved in addition to quantify the acceptable risk, often in the…
Traditional reachability methods provide formal guarantees of safety under bounded disturbances. However, they strictly enforce state constraints as inviolable, which can result in overly conservative or infeasible solutions in complex…
Adversarial attacks pose significant threats to deploying state-of-the-art classifiers in safety-critical applications. Two classes of methods have emerged to address this issue: empirical defences and certified defences. Although certified…
Machine learning has achieved great success in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Most existing BCI studies focused on improving the decoding accuracy, with only a few considering the adversarial security.…
Standard inference about a scalar parameter estimated via GMM amounts to applying a t-test to a particular set of observations. If the number of observations is not very large, then moderately heavy tails can lead to poor behavior of the…
Background: Ventilator-associated pneumonia (VAP) in traumatic brain injury (TBI) patients poses a significant mortality risk and imposes a considerable financial burden on patients and healthcare systems. Timely detection and…
Cyber situational awareness has been proven to be of value in forming a comprehensive understanding of threats and vulnerabilities within organisations, as the degree of exposure is governed by the prevailing levels of cyber-hygiene and…
We develop a new method for proving explicit approximation lower bounds for TSP problems with bounded metrics improving on the best up to now known bounds. They almost match the best known bounds for unbounded metric TSP problems. In…
Modern automated surveillance techniques are heavily reliant on deep learning methods. Despite the superior performance, these learning systems are inherently vulnerable to adversarial attacks - maliciously crafted inputs that are designed…
Over the past few years, the emergence of backdoor attacks has presented significant challenges to deep learning systems, allowing attackers to insert backdoors into neural networks. When data with a trigger is processed by a backdoor…
Cyber resilience is the ability of a system to resist and recover from a cyber attack, thereby restoring the system's functionality. Effective design and development of a cyber resilient system requires experimental methods and tools for…