Large Language Models (LLMs) have achieved human-level fluency in text generation, making it difficult to distinguish between human-written and LLM-generated texts. This poses a growing risk of misuse of LLMs and demands the development of detectors to identify LLM-generated texts. However, existing detectors lack robustness against attacks: they degrade detection accuracy by simply paraphrasing LLM-generated texts. Furthermore, a malicious user might attempt to deliberately evade the detectors based on detection results, but this has not been assumed in previous studies. In this paper, we propose OUTFOX, a framework that improves the robustness of LLM-generated-text detectors by allowing both the detector and the attacker to consider each other's output. In this framework, the attacker uses the detector's prediction labels as examples for in-context learning and adversarially generates essays that are harder to detect, while the detector uses the adversarially generated essays as examples for in-context learning to learn to detect essays from a strong attacker. Experiments in the domain of student essays show that the proposed detector improves the detection performance on the attacker-generated texts by up to +41.3 points in F1-score. Furthermore, the proposed detector shows a state-of-the-art detection performance: up to 96.9 points in F1-score, beating existing detectors on non-attacked texts. Finally, the proposed attacker drastically degrades the performance of detectors by up to -57.0 points F1-score, massively outperforming the baseline paraphrasing method for evading detection.

This paper examines the current landscape of AI regulations, highlighting the divergent approaches being taken, and proposes an alternative contextual, coherent, and commensurable (3C) framework. The EU, Canada, South Korea, and Brazil follow a horizontal or lateral approach that postulates the homogeneity of AI systems, seeks to identify common causes of harm, and demands uniform human interventions. In contrast, the U.K., Israel, Switzerland, Japan, and China have pursued a context-specific or modular approach, tailoring regulations to the specific use cases of AI systems. The U.S. is reevaluating its strategy, with growing support for controlling existential risks associated with AI. Addressing such fragmentation of AI regulations is crucial to ensure the interoperability of AI. The present degree of proportionality, granularity, and foreseeability of the EU AI Act is not sufficient to garner consensus. The context-specific approach holds greater promises but requires further development in terms of details, coherency, and commensurability. To strike a balance, this paper proposes a hybrid 3C framework. To ensure contextuality, the framework categorizes AI into distinct types based on their usage and interaction with humans: autonomous, allocative, punitive, cognitive, and generative AI. To ensure coherency, each category is assigned specific regulatory objectives: safety for autonomous AI; fairness and explainability for allocative AI; accuracy and explainability for punitive AI; accuracy, robustness, and privacy for cognitive AI; and the mitigation of infringement and misuse for generative AI. To ensure commensurability, the framework promotes the adoption of international industry standards that convert principles into quantifiable metrics. In doing so, the framework is expected to foster international collaboration and standardization without imposing excessive compliance costs.

Machine Learning (ML) has been widely applied to cybersecurity and is considered state-of-the-art for solving many of the open issues in that field. However, it is very difficult to evaluate how good the produced solutions are, since the challenges faced in security may not appear in other areas. One of these challenges is the concept drift, which increases the existing arms race between attackers and defenders: malicious actors can always create novel threats to overcome the defense solutions, which may not consider them in some approaches. Due to this, it is essential to know how to properly build and evaluate an ML-based security solution. In this paper, we identify, detail, and discuss the main challenges in the correct application of ML techniques to cybersecurity data. We evaluate how concept drift, evolution, delayed labels, and adversarial ML impact the existing solutions. Moreover, we address how issues related to data collection affect the quality of the results presented in the security literature, showing that new strategies are needed to improve current solutions. Finally, we present how existing solutions may fail under certain circumstances, and propose mitigations to them, presenting a novel checklist to help the development of future ML solutions for cybersecurity.

Financial fraud detection is essential for preventing significant financial losses and maintaining the reputation of financial institutions. However, conventional methods of detecting financial fraud have limited effectiveness, necessitating the need for new approaches to improve detection rates. In this paper, we propose a novel approach for detecting financial fraud using Quantum Graph Neural Networks (QGNNs). QGNNs are a type of neural network that can process graph-structured data and leverage the power of Quantum Computing (QC) to perform computations more efficiently than classical neural networks. Our approach uses Variational Quantum Circuits (VQC) to enhance the performance of the QGNN. In order to evaluate the efficiency of our proposed method, we compared the performance of QGNNs to Classical Graph Neural Networks using a real-world financial fraud detection dataset. The results of our experiments showed that QGNNs achieved an AUC of $0.85$, which outperformed classical GNNs. Our research highlights the potential of QGNNs and suggests that QGNNs are a promising new approach for improving financial fraud detection.

More than 10.7% of people aged 65 and older are affected by Alzheimer's disease. Early diagnosis and treatment are crucial as most Alzheimer's patients are unaware of having it until the effects become detrimental. AI has been known to use magnetic resonance imaging (MRI) to diagnose Alzheimer's. However, models which produce low rates of false diagnoses are critical to prevent unnecessary treatments. Thus, we trained supervised Random Forest models with segmented brain volumes and Convolutional Neural Network (CNN) outputs to classify different Alzheimer's stages. We then applied out-of-distribution (OOD) detection to the CNN model, enabling it to report OOD if misclassification is likely, thereby reducing false diagnoses. With an accuracy of 98% for detection and 95% for classification, our model based on CNN results outperformed our segmented volume model, which had detection and classification accuracies of 93% and 87%, respectively. Applying OOD detection to the CNN model enabled it to flag brain tumor images as OOD with 96% accuracy and minimal overall accuracy reduction. By using OOD detection to enhance the reliability of MRI classification using CNNs, we lowered the rate of false positives and eliminated a significant disadvantage of using Machine Learning models for healthcare tasks.

Accurate predictions of electricity demands are necessary for managing operations in a small aggregation load setting like a Microgrid. Due to low aggregation, the electricity demands can be highly stochastic and point estimates would lead to inflated errors. Interval estimation in this scenario, would provide a range of values within which the future values might lie and helps quantify the errors around the point estimates. This paper introduces a residual bootstrap algorithm to generate interval estimates of day-ahead electricity demand. A machine learning algorithm is used to obtain the point estimates of electricity demand and respective residuals on the training set. The obtained residuals are stored in memory and the memory is further partitioned. Days with similar demand patterns are grouped in clusters using an unsupervised learning algorithm and these clusters are used to partition the memory. The point estimates for test day are used to find the closest cluster of similar days and the residuals are bootstrapped from the chosen cluster. This algorithm is evaluated on the real electricity demand data from EULR(End Use Load Research) and is compared to other bootstrapping methods for varying confidence intervals.

Bruna Moreira da Silva is a PhD student at The University of Melbourne. Her research interests are in bioinformatics, immunoinformatics and machine learning to advance Global Health. David B. Ascher is the Director of Biotechnology at the University of Queensland and head of Computational Biology and Clinical Informatics at the Baker Institute and Systems and Computational Biology at Bio21 Institute. He is interested in developing and applying computational tools to assist leveraging clinical and omics data for drug discovery and personalised medicine. Nicholas Geard is an Associate Professor at the School of Computing and Information Systems at the University of Melbourne and Director of the Melbourne Data Analytics Platform. He is a computer scientist specialising in computational simulation applied to a range of problems in health and epidemiology. Douglas E. V. Pires is an Associate Professor in Digital Health at the School of Computing and Information Systems at the University of Melbourne and group leader at the Bio21 Institute. He is a computer scientist and bioinformatician specialising in machine learning and AI and the development of the next generation of tools to analyse omics data, and guide drug discovery and personalised medicine. ABSTRACT Antibodies, a prominent class of approved biologics, play a crucial role in detecting foreign antigens. The effectiveness of antigen neutralisation and elimination hinges upon the strength, sensitivity, and specificity of the paratope-epitope interaction, which demands resource-intensive experimental techniques for characterisation. In recent years, artificial intelligence and machine learning methods have made significant strides, revolutionising the prediction of protein structures and their complexes. The past decade has also witnessed the evolution of computational approaches aiming to support immunotherapy design. This review focuses on the progress of machine learning-based tools and their frameworks in the domain of B-cell immunotherapy design, encompassing linear and conformational epitope prediction, paratope prediction, and antibody design. We mapped the most commonly used data sources, evaluation metrics, and method availability and thoroughly assessed their significance and limitations, discussing the main challenges ahead. INTRODUCTION Therapeutic antibodies are a rapidly growing class of biopharmaceuticals with potentially exceptional antigen specificity and affinity. Their ability to detect and eliminate a wide array of foreign threats makes them suitable for a range of potential therapeutic and diagnostic applications. Antibody and antigen engineering have been greatly benefited by the evolution of research in computational biology, leading to innovative approaches in screening antibody targets, optimising their biochemical and physical properties, predicting and optimising binding affinity and understanding escape mutations [1].

The protection of Industrial Control Systems (ICS) that are employed in public critical infrastructures is of utmost importance due to catastrophic physical damages cyberattacks may cause. The research community requires testbeds for validation and comparing various intrusion detection algorithms to protect ICS. However, there exist high barriers to entry for research and education in the ICS cybersecurity domain due to expensive hardware, software, and inherent dangers of manipulating real-world systems. To close the gap, built upon recently developed 3D high-fidelity simulators, we further showcase our integrated framework to automatically launch cyberattacks, collect data, train machine learning models, and evaluate for practical chemical and manufacturing processes. On our testbed, we validate our proposed intrusion detection model called Minimal Threshold and Window SVM (MinTWin SVM) that utilizes unsupervised machine learning via a one-class SVM in combination with a sliding window and classification threshold. Results show that MinTWin SVM minimizes false positives and is responsive to physical process anomalies. Furthermore, we incorporate our framework with ICS cybersecurity education by using our dataset in an undergraduate machine learning course where students gain hands-on experience in practicing machine learning theory with a practical ICS dataset. All of our implementations have been open-sourced.

Machine learning systems produce biased results towards certain demographic groups, known as the fairness problem. Recent approaches to tackle this problem learn a latent code (i.e., representation) through disentangled representation learning and then discard the latent code dimensions correlated with sensitive attributes (e.g., gender). Nevertheless, these approaches may suffer from incomplete disentanglement and overlook proxy attributes (proxies for sensitive attributes) when processing real-world data, especially for unstructured data, causing performance degradation in fairness and loss of useful information for downstream tasks. In this paper, we propose a novel fairness framework that performs debiasing with regard to both sensitive attributes and proxy attributes, which boosts the prediction performance of downstream task models without complete disentanglement. The main idea is to, first, leverage gradient-based explanation to find two model focuses, 1) one focus for predicting sensitive attributes and 2) the other focus for predicting downstream task labels, and second, use them to perturb the latent code that guides the training of downstream task models towards fairness and utility goals. We show empirically that our framework works with both disentangled and non-disentangled representation learning methods and achieves better fairness-accuracy trade-off on unstructured and structured datasets than previous state-of-the-art approaches.

Audio is one of the most used ways of human communication, but at the same time it can be easily misused to trick people. With the revolution of AI, the related technologies are now accessible to almost everyone thus making it simple for the criminals to commit crimes and forgeries. In this work, we introduce a neural network method to develop a classifier that will blindly classify an input audio as real or mimicked; the word 'blindly' refers to the ability to detect mimicked audio without references or real sources. The proposed model was trained on a set of important features extracted from a large dataset of audios to get a classifier that was tested on the same set of features from different audios. The data was extracted from two raw datasets, especially composed for this work; an all English dataset and a mixed dataset (Arabic plus English). These datasets have been made available, in raw form, through GitHub for the use of the research community at https://github.com/SaSs7/Dataset. For the purpose of comparison, the audios were also classified through human inspection with the subjects being the native speakers. The ensued results were interesting and exhibited formidable accuracy.