Search

Background: Many open-source skin cancer image datasets are the result of clinical trials conducted in countries with lighter skin tones. Due to this tone imbalance, machine learning models derived from these datasets can perform well at detecting skin cancer for lighter skin tones. Any tone bias in these models could introduce fairness concerns and reduce public trust in the artificial intelligence health field. Methods: We examine a subset of images from the International Skin Imaging Collaboration (ISIC) archive that provide tone information. The subset has a significant tone imbalance. These imbalances could explain a model's tone bias. To address this, we train models using the imbalanced dataset and a balanced dataset to compare against. The datasets are used to train a deep convolutional neural network model to classify the images as malignant or benign. We then evaluate the models' disparate impact, based on selection rate, relative to dark or light skin tone. Results: Using the imbalanced dataset, we found that the model is significantly better at detecting malignant images in lighter tone resulting in a disparate impact of 0.577. Using the balanced dataset, we found that the model is also significantly better at detecting malignant images in lighter versus darker tones with a disparate impact of 0.684. Using the imbalanced or balanced dataset to train the model still results in a disparate impact well below the standard threshold of 0.80 which suggests the model is biased with respect to skin tone. Conclusion: The results show that typical skin cancer machine learning models can be tone biased. These results provide evidence that diagnosis or tone imbalance is not the cause of the bias. Other techniques will be necessary to identify and address the bias in these models, an area of future investigation.

Advancements in wireless communication and the increased accessibility to low-cost sensing and data processing IoT technologies have increased the research and development of urban monitoring systems. Most smart city research projects rely on deploying proprietary IoT testbeds for indoor and outdoor data collection. Such testbeds typically rely on a three-tier architecture composed of the Endpoint, the Edge, and the Cloud. Managing the system's operation whilst considering the security and privacy challenges that emerge, such as data privacy controls, network security, and security updates on the devices, is challenging. This work presents a systematic study of the challenges of developing, deploying and managing urban monitoring testbeds, as experienced in a series of urban monitoring research projects, followed by an analysis of the relevant literature. By identifying the challenges in the various projects and organising them under the V-model development lifecycle levels, we provide a reference guide for future projects. Understanding the challenges early on will facilitate current and future smart-cities IoT research projects to reduce implementation time and deliver secure and resilient testbeds., Comment: 25 pages, under review

Content ratings can enable audiences to determine the suitability of various media products. With the recent advent of fan fiction, the critical issue of fan fiction content ratings has emerged. Whether fan fiction content ratings are done voluntarily or required by regulation, there is the need to automate the content rating classification. The problem is to take fan fiction text and determine the appropriate content rating. Methods for other domains, such as online books, have been attempted though none have been applied to fan fiction. We propose natural language processing techniques, including traditional and deep learning methods, to automatically determine the content rating. We show that these methods produce poor accuracy results for multi-classification. We then demonstrate that treating the problem as a binary classification problem produces better accuracy. Finally, we believe and provide some evidence that the current approach of self-annotating has led to incorrect labels limiting classification results., Comment: 10 pages, 6 figures, 6 tables

Security research has concentrated on converting operating system audit logs into suitable graphs, such as provenance graphs, for analysis. However, provenance graphs can grow very large requiring significant computational resources beyond what is necessary for many security tasks and are not feasible for resource constrained environments, such as edge devices. To address this problem, we present the \textit{resource-interaction graph} that is built directly from the audit log. We show that the resource-interaction graph's storage requirements are significantly lower than provenance graphs using an open-source data set with two container escape attacks captured from an edge device. We use a graph autoencoder and graph clustering technique to evaluate the representation for an anomaly detection task. Both approaches are unsupervised and are thus suitable for detecting zero-day attacks. The approaches can achieve f1 scores typically over 80\% and in some cases over 90\% for the selected data set and attacks., Comment: 15 pages, 11 figures, 6 tables, for dataset see https://github.com/jpope8/container-escape-dataset, for code see https://github.com/jpope8/container-escape-analysis

Data integrity becomes paramount as the number of Internet of Things (IoT) sensor deployments increases. Sensor data can be altered by benign causes or malicious actions. Mechanisms that detect drifts and irregularities can prevent disruptions and data bias in the state of an IoT application. This paper presents LE3D, an ensemble framework of data drift estimators capable of detecting abnormal sensor behaviours. Working collaboratively with surrounding IoT devices, the type of drift (natural/abnormal) can also be identified and reported to the end-user. The proposed framework is a lightweight and unsupervised implementation able to run on resource-constrained IoT devices. Our framework is also generalisable, adapting to new sensor streams and environments with minimal online reconfiguration. We compare our method against state-of-the-art ensemble data drift detection frameworks, evaluating both the real-world detection accuracy as well as the resource utilisation of the implementation. Experimenting with real-world data and emulated drifts, we show the effectiveness of our method, which achieves up to 97% of detection accuracy while requiring minimal resources to run., Comment: IEEE CCNC 2023, Las Vegas, USA

In this paper we study the prediction of heart rate from acceleration using a wrist worn wearable. Although existing photoplethysmography (PPG) heart rate sensors provide reliable measurements, they use considerably more energy than accelerometers and have a major impact on battery life of wearable devices. By using energy-efficient accelerometers to predict heart rate, significant energy savings can be made. Further, we are interested in understanding patient recovery after a heart rate intervention, where we expect a variation in heart rate over time. Therefore, we propose an online approach to tackle the concept as time passes. We evaluate the methods on approximately 4 weeks of free living data from three patients over a number of months. We show that our approach can achieve good predictive performance (e.g., 2.89 Mean Absolute Error) while using the PPG heart rate sensor infrequently (e.g., 20.25% of the samples)., Comment: MLMH 2018: 2018 KDD Workshop on Machine Learning for Medicine and Healthcare

The assumption of free will - the ability of an experimentalist to make random choices - is central to proving the indeterminism of quantum resources, the primary tool in quantum cryptography. Relaxing the assumption in a Bell test allows violation of the usual classical threshold by correlating the random number generators used to select measurements with the devices that perform them. In this paper, we examine not only these correlations, but those across multiple runs of the experiment. This enables an explicit exposition of the optimal cheating strategy and how the correlations manifest themselves within this strategy. Similar to other recent results, we prove that there remain Bell violations for a sufficiently high, yet non-maximal degree of free will which cannot be simulated by a classical attack, regardless of how many runs of the experiment those choices are correlated over., Comment: 8 pages, 3 figures. Version 2 reflects the published paper in Physical Review A, which among some minor additions/changes now includes Section V discussing the numerical approach to Bell inequalities other than CHSH

With the advent of quantum information, the violation of a Bell inequality is used as evidence of the absence of an eavesdropper in cryptographic scenarios such as key distribution and randomness expansion. One of the key assumptions of Bell's Theorem is the existence of experimental "free will", meaning that measurement settings can be chosen at random and independently by each party. The relaxation of this assumption potentially shifts the balance of power towards an eavesdropper. We consider a no-signalling model with reduced "free will" and bound the adversary's capabilities in the task of randomness expansion., Comment: 7 pages, 2 figures