--Alzheimer's Disease (AD) is a progressive, irreversible neurodegenerative disorder that often originates from Mild Cognitive Impairment (MCI). This progression results in significant memory loss and severely affects patients' quality of life. Clinical trials have consistently shown that early and targeted interventions for individuals with MCI may slow or even prevent the advancement of AD. Research indicates that accurate medical classification requires diverse multimodal data, including detailed assessment scales and neuroimaging techniques like Magnetic Resonance Imaging (MRI) and Positron Emission T omography (PET). However, simultaneously collecting the aforementioned three modalities for training presents substantial challenges. T o tackle these difficulties, we propose GFE-Mamba, a multimodal classifier founded on Generative Feature Extractor . The intermediate features provided by this Extractor can compensate for the shortcomings of PET and achieve profound multimodal fusion in the classifier . The Mamba block, as the backbone of the classifier, enables it to efficiently extract information from long-sequence scale information. We provide our rationale for developing this cross-temporal progression prediction dataset and the pre-trained Extractor weights. Our experimental findings reveal that the GFE-Mamba model effectively predicts the progression from MCI to AD and surpasses several leading methods in the field. Data used in the preparation of this article was obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). The ADNI researchers contributed data but did not participate in analysis or writing of this report. The data was made available at the ADNI database (www.loni.usc.edu). Changbiao Chu is with Xuanwu Hospital, Capital Medical University, Beijing, 100053, China (e-mail:chucb@xwhosp.org). LZHEIMER'S Disease (AD) is a prevalent neurode-generative condition in older adults, affecting memory, cognitive abilities, and daily life activities [41].

Objective: This work explores use of a few-shot transfer learning method to train and implement a convolutional spiking neural network (CSNN) on a BrainChip Akida AKD1000 neuromorphic system-on-chip for developing individual-level, instead of traditionally used group-level, models using electroencephalographic data. The efficacy of the method is studied on an advanced driver assist system related task of predicting braking intention. Main Results: Efficacy of the above methodology to develop individual specific braking intention predictive models by rapidly adapting the group-level model in as few as three training epochs while achieving at least 90% accuracy, true positive rate and true negative rate is presented. Further, results show an energy reduction of over 97% with only a 1.3x increase in latency when using the Akida AKD1000 processor for network inference compared to an Intel Xeon CPU. Similar results were obtained in a subsequent ablation study using a subset of five out of 19 channels. Significance: Especially relevant to real-time applications, this work presents an energy-efficient, few-shot transfer learning method that is implemented on a neuromorphic processor capable of training a CSNN as new data becomes available, operating conditions change, or to customize group-level models to yield personalized models unique to each individual.

Most existing membership inference attacks (MIAs) utilize metrics (e.g., loss) calculated on the model's final state, while recent advanced attacks leverage metrics computed at various stages, including both intermediate and final stages, throughout the model training. Nevertheless, these attacks often process multiple intermediate states of the metric independently, ignoring their time-dependent patterns. Consequently, they struggle to effectively distinguish between members and non-members who exhibit similar metric values, particularly resulting in a high false-positive rate. In this study, we delve deeper into the new membership signals in the black-box scenario. We identify a new, more integrated membership signal: the Pattern of Metric Sequence, derived from the various stages of model training. We contend that current signals provide only partial perspectives of this new signal: the new one encompasses both the model's multiple intermediate and final states, with a greater emphasis on temporal patterns among them. Building upon this signal, we introduce a novel attack method called Sequential-metric based Membership Inference Attack (SeqMIA). Specifically, we utilize knowledge distillation to obtain a set of distilled models representing various stages of the target model's training. We then assess multiple metrics on these distilled models in chronological order, creating distilled metric sequence. We finally integrate distilled multi-metric sequences as a sequential multiformat and employ an attention-based RNN attack model for inference. Empirical results show SeqMIA outperforms all baselines, especially can achieve an order of magnitude improvement in terms of TPR @ 0.1% FPR. Furthermore, we delve into the reasons why this signal contributes to SeqMIA's high attack performance, and assess various defense mechanisms against SeqMIA.

In the intensive care unit, the capability to predict the need for mechanical ventilation (MV) facilitates more timely interventions to improve patient outcomes. Recent works have demonstrated good performance in this task utilizing machine learning models. This paper explores the novel application of a deep learning model with multi-head attention (FFNN-MHA) to make more accurate MV predictions and reduce false positives by learning personalized contextual information of individual patients. Utilizing the publicly available MIMIC-IV dataset, FFNN-MHA demonstrates an improvement of 0.0379 in AUC and a 17.8\% decrease in false positives compared to baseline models such as feed-forward neural networks. Our results highlight the potential of the FFNN-MHA model as an effective tool for accurate prediction of the need for mechanical ventilation in critical care settings.

Histopathological image classification constitutes a pivotal task in computer-aided diagnostics. The precise identification and categorization of histopathological images are of paramount significance for early disease detection and treatment. In the diagnostic process of pathologists, a multi-tiered approach is typically employed to assess abnormalities in cell regions at different magnifications. However, feature extraction is often performed at a single granularity, overlooking the multi-granular characteristics of cells. To address this issue, we propose the Fuzzy-guided Multi-granularity Deep Neural Network (FMDNN). Inspired by the multi-granular diagnostic approach of pathologists, we perform feature extraction on cell structures at coarse, medium, and fine granularity, enabling the model to fully harness the information in histopathological images. We incorporate the theory of fuzzy logic to address the challenge of redundant key information arising during multi-granular feature extraction. Cell features are described from different perspectives using multiple fuzzy membership functions, which are fused to create universal fuzzy features. A fuzzy-guided cross-attention module guides universal fuzzy features toward multi-granular features. We propagate these features through an encoder to all patch tokens, aiming to achieve enhanced classification accuracy and robustness. In experiments on multiple public datasets, our model exhibits a significant improvement in accuracy over commonly used classification methods for histopathological image classification and shows commendable interpretability.

This paper investigates the threat of backdoors in Deep Reinforcement Learning (DRL) agent policies and proposes a novel method for their detection at runtime. Our study focuses on elusive in-distribution backdoor triggers. Such triggers are designed to induce a deviation in the behaviour of a backdoored agent while blending into the expected data distribution to evade detection. Through experiments conducted in the Atari Breakout environment, we demonstrate the limitations of current sanitisation methods when faced with such triggers and investigate why they present a challenging defence problem. We then evaluate the hypothesis that backdoor triggers might be easier to detect in the neural activation space of the DRL agent's policy network. Our statistical analysis shows that indeed the activation patterns in the agent's policy network are distinct in the presence of a trigger, regardless of how well the trigger is concealed in the environment. Based on this, we propose a new defence approach that uses a classifier trained on clean environment samples and detects abnormal activations. Our results show that even lightweight classifiers can effectively prevent malicious actions with considerable accuracy, indicating the potential of this research direction even against sophisticated adversaries.

Large Language Models (LLMs) have demonstrated significant potential in causal discovery tasks by utilizing their vast expert knowledge from extensive text corpora. However, the multi-agent capabilities of LLMs in causal discovery remain underexplored. This paper introduces a general framework to investigate this potential. The first is the Meta Agents Model, which relies exclusively on reasoning and discussions among LLM agents to conduct causal discovery. The second is the Coding Agents Model, which leverages the agents' ability to plan, write, and execute code, utilizing advanced statistical libraries for causal discovery. The third is the Hybrid Model, which integrates both the Meta Agents Model and Coding Agents Model approaches, combining the statistical analysis and reasoning skills of multiple agents. Our proposed framework shows promising results by effectively utilizing LLMs' expert knowledge, reasoning capabilities, multi-agent cooperation, and statistical causal methods. By exploring the multi-agent potential of LLMs, we aim to establish a foundation for further research in utilizing LLMs multi-agent for solving causal-related problems.

In this paper, we propose an experimental investigation of the problem of AI fairness in classification. We train an AI model and develop our own fairness package FairDream to detect inequalities and then to correct for them, using income prediction as a case study. Our experiments show that it is a property of FairDream to fulfill fairness objectives which are conditional on the ground truth (Equalized Odds), even when the algorithm is set the task of equalizing positives across groups (Demographic Parity). While this may be seen as an anomaly, we explain this property by comparing our approach with a closely related fairness method (GridSearch), which can enforce Demographic Parity at the expense of Equalized Odds. We grant that a fairness metric conditioned on true labels does not give a sufficient criterion to reach fairness, but we argue that it gives us at least a necessary condition to implement Demographic Parity cautiously. We also explain why neither Equal Calibration nor Equal Precision stand as relevant fairness criteria in classification. Addressing their limitations to warn the decision-maker for any disadvantaging rate, Equalized Odds avoids the peril of strict conservatism, while keeping away the utopia of a whole redistribution of resources through algorithms.

Decentralized Federated Anomaly Detection in Smart Grids: A P2P Gossip Approach Muhammad Akbar Husnoo a,, Adnan Anwar a, Md Enamul Haque b and Abdun Naser Mahmood c a Centre for Cyber Resilience and Trust (CREST), Deakin University, 75 Pigdons Rd, Waurn Ponds, 3216, Victoria, Australia b Centre for Smart Power and Energy Research (CSPER)), Deakin University, 75 Pigdons Rd, Waurn Ponds, 3216, Victoria, Australia c Department of Computer Science & IT, Latrobe University, Plenty Rd, Bundoora, 3086, Victoria, AustraliaA R T I C L E I N F OKeywords: Anomaly Detection Decentralized Federated Learning (DFL) Cyberattack Internet of Things (Io T) Smart Grid A B S T R A C T Amidst escalating concerns regarding security and privacy within the Smart Grid domain, the need for robust intrusion detection mechanisms in critical energy infrastructure has surged in recent times. To address the challenges posed by privacy preservation and decentralized power zones with distinct data ownership, Federated Learning (FL) has emerged as a promising privacy-preserving solution which facilitates collaborative training of attack detection models without necessitating the sharing of raw data. However, FL presents several implementation limitations in the power system domain due to its heavy reliance on a centralized aggregator and the risks of privacy leakage during model update transmission. In response to the technical bottlenecks, this paper introduces a novel decentralized federated anomaly detection scheme based on two main gossip protocols namely Random Walk and Epidemic. Our findings indicate that the Random Walk protocol exhibits superior performance compared to the Epidemic protocol, highlighting its efficacy in decentralized federated learning environments. Experimental validation of the proposed framework utilizing publicly available industrial control systems datasets demonstrates superior attack detection accuracy while safeguarding data confidentiality and mitigating the impact of communication latency and stragglers. Moreover, a notable 35% improvement in training time against conventional FL highlights the efficacy and robustness of our decentralized learning approach.1.

Given the magnitude of data generation currently, both in quantity and speed, the use of machine learning is increasingly important. When data include protected features that might give rise to discrimination, special care must be taken. Data quality is critical in these cases, as biases in training data can be reflected in classification models. This has devastating consequences and fails to comply with current regulations. Data-Centric Artificial Intelligence proposes dataset modifications to improve its quality. Instance selection via undersampling can foster balanced learning of classes and protected feature values in the classifier. When such undersampling is done close to the decision boundary, the effect on the classifier would be bolstered. This work proposes Fair Overlap Number of Balls (Fair-ONB), an undersampling method that harnesses the data morphology of the different data groups (obtained from the combination of classes and protected feature values) to perform guided undersampling in the areas where they overlap. It employs attributes of the ball coverage of the groups, such as the radius, number of covered instances and density, to select the most suitable areas for undersampling and reduce bias. Results show that the Fair-ONB method reduces bias with low impact on the classifier's predictive performance.