Machine unlearning, which is crucial for data privacy and regulatory compliance, involves the selective removal of specific information from a machine learning model. This study focuses on ...implementing machine unlearning in Spiking Neuron Models (SNMs) that closely mimic biological neural network behaviors, aiming to enhance both flexibility and ethical compliance of AI models. We introduce a novel hybrid approach for machine unlearning in SNMs, which combines selective synaptic retraining, synaptic pruning, and adaptive neuron thresholding. This methodology is designed to effectively eliminate targeted information while preserving the overall integrity and performance of the neural network. Extensive experiments were conducted on various computer vision datasets to assess the impact of machine unlearning on critical performance metrics such as accuracy, precision, recall, and ROC AUC. Our findings indicate that the hybrid approach not only maintains but in some cases enhances the neural network's performance post-unlearning. The results confirm the practicality and efficiency of our approach, underscoring its applicability in real-world AI systems.
The soaring popularity of smart devices equipped with electrocardiograms (ECG) is driving a nationwide craze for predicting heart abnormalities. Smart ECG monitoring system has achieved significant ...success by training machine learning models on massive amounts of user data. However, three issues arise accordingly: 1) ECG data collected from various devices may display personal characteristic variations, leading to non-independent and identically distributed (non-i.i.d.) data. These differences can impact the accuracy and reliability of data analysis and interpretation; 2) Most ECG data on smart devices is unlabeled, and data labeling is resource-consuming as it requires heavy-loaded labeling from professionals; 3) While centralizing data for machine learning can address above issues like non-i.i.d. data and labeling difficulties, it may compromise personal privacy. To tackle these three issues, we introduce a novel federated semi-supervised learning (FSSL) framework named FedECG for ECG abnormalities prediction. Specifically, we adopt a pre-processing module to better utilize the ECG data. Next, we devise a novel model based on ResNet-9 in FSSL to accurately predict abnormal signals from ECG recordings. In addition, we incorporate pseudo-labeling and data augmentation techniques to enhance our implemented semi-supervised learning. We also develop a model aggregation algorithm to improve the model convergence performance in federated learning. Finally, we conduct simulations on a real-world dataset. Experiments demonstrate that FedECG obtains 94.8% accuracy with only 50% of the data labeled. FedECG achieved slightly lower accuracy than traditional centralized methods in ECG monitoring, with a 2% reduction. In contrast, FedECG outperforms the state-of-the-art distributed methods by about 3%. Moreover, FedECG can also support unlabeled data and preserve data privacy as well.
According to the WHO, anemia is a highly prevalent disease, especially for patients in the emergency department. The pathophysiological mechanism by which anemia can affect facial characteristics, ...such as membrane pallor, has been proven to detect anemia with the help of deep learning technology. The quick prediction method for the patient in the emergency department is important to screen the anemic state and judge the necessity of blood transfusion treatment.
We trained a deep learning system to predict anemia using videos of 316 patients. All the videos were taken with the same portable pad in the ambient environment of the emergency department. The video extraction and face recognition methods were used to highlight the facial area for analysis. Accuracy and area under the curve were used to assess the performance of the machine learning system at the image level and the patient level.
Three tasks were applied for performance evaluation. The objective of Task 1 was to predict patients' anemic states hemoglobin (Hb) <13 g/dl in men and Hb <12 g/dl in women. The accuracy of the image level was 82.37%, the area under the curve (AUC) of the image level was 0.84, the accuracy of the patient level was 84.02%, the sensitivity of the patient level was 92.59%, and the specificity of the patient level was 69.23%. The objective of Task 2 was to predict mild anemia (Hb <9 g/dl). The accuracy of the image level was 68.37%, the AUC of the image level was 0.69, the accuracy of the patient level was 70.58%, the sensitivity was 73.52%, and the specificity was 67.64%. The aim of task 3 was to predict severe anemia (Hb <7 g/dl). The accuracy of the image level was 74.01%, the AUC of the image level was 0.82, the accuracy of the patient level was 68.42%, the sensitivity was 61.53%, and the specificity was 83.33%.
The machine learning system could quickly and accurately predict the anemia of patients in the emergency department and aid in the treatment decision for urgent blood transfusion. It offers great clinical value and practical significance in expediting diagnosis, improving medical resource allocation, and providing appropriate treatment in the future.
In mass casualty incidents (MCI), the number of casualties can far exceed the capacity of medical emergency units to treat and transport in a very short period of time. A rapid MCI triage according ...to the severity of their injuries, can not only effectively use limited medical resources, but also improve the survival rate of injured patients. With the emergence of artificial intelligence (AI) and augmented reality (AR), smart glasses have been developed and used in different scenarios, and have achieved remarkable results in the medical field. This article focuses on the role and advantages of smart glasses in the triage of MCI, while proposing the problems in the application of smart glasses. At the same time, we elaborate on the development status of smart glasses in the triage, and discuss the application trend and development direction of smart glasses in the triage of pre-hospital injuries.
•We propose a novel federated learning scheme using knowledge distillation technology for heterogeneous model architecture called MHAT.•We train an auxiliary model on the server to realize ...information aggregation, which significantly improves the speed of model convergence while maintaining acceptable model convergence accuracy.•We conduct various experiments to validate our scheme achieves a good performance.
Federated Learning allows multiple participants to jointly train a global model while guaranteeing the confidentiality and integrity of private datasets. However, current server aggregation algorithms for federated learning only focus on model parameters, resulting in heavy communication costs and low convergence speed. Most importantly, they are unable to handle the scenario wherein different clients hold different local models with various network architectures. In this paper, we view these challenges from an alternative perspective: we draw attention to what should be aggregated and how to improve convergence efficiency. Specifically, we propose MHAT, a novel model-heterogenous aggregation training federated learning scheme which exploits a technique of Knowledge Distillation (KD) to extract the update information of the heterogenous model of all clients and trains an auxiliary model on the server to realize information aggregation. MHAT relaxes clients from fixing on an unified model architecture and significantly reduces the required computing resources while maintaining acceptable model convergence accuracy. Various experiments verify the effectiveness and applicability of our proposed scheme.
•This paper proposes PNAS, a novel privacy preserving training framework for MLaaS scenarios, supports the optimization for both network parameter and model architecture.•We design a double ...encryption scheme for PNAS. Our scheme eliminates privacy leakage during remote training. Samples and their corresponding labels, as well as intermediate feature maps are well protected from an untrusted server.•We implement a prototype PNAS and evaluate its performance. Experimental result shows that PNAS is able to deliver models with higher accuracy.
The success of deep neural networks has contributed to many fields, such as finance, medic and speech recognition. Machine learning models adopted in these fields are always trained with a massive amount of distributed and highly personalized data harvested directly from users. Concerns for data privacy and the demand for better data exploitation have prompted the design of several secure schemes that allow an untrusted server to train ML models for one or multiple parties. However, these existing schemes only focus on network parameter, and hardly extend their optimization range to model architecture scope. Sine the performance of a neural network is closely related to both parameter and its architecture, service providers are difficult to deliver customized and flexible neural networks to each client. To this end, in this paper we propose PNAS, a novel MLaaS framework that enables a server to jointly optimize network parameter and architecture while ensuring the privacy of training sets. A double-encryption scheme is derived to prevent privacy leakage from sample itself, as well as intermediate feature maps during training. Specifically, we adopt functional encryption and feature transformation to secure forward and back propagation. Extensive experiments have demonstrated the superiority of our proposal.
Abstract
Traditional steam turbine maintenance work has many shortcomings, such as poor effectiveness, high cost, and long cycle. In order to solve this problem and improve the professional skills ...and maintenance efficiency of steam turbine maintenance personnel, we first collect steam turbine equipment drawings and 3D dimension data of parts, and use 3D modeling software to establish augmented reality scene model. Then combined with the virtual reality technology and image fusion technology to realize the maintenance procedure training and maintenance auxiliary guidance of the steam turbine unit. The practical application results show that this technology can realize the virtual and real operation of the model by users in augmented reality scenes, bring interactive and immersive experience to operators, and improve the work efficiency of maintenance personnel.
Jointly learning from multiple datasets can help building versatile intelligent systems yet may give rise to serious concerns of data privacy and model selection. Specifically, on the one hand, these ...datasets can be distributed at various local clients, who may not be willing or do not ought to share data with each other. On the other hand, it is unrealistic to choose a model architecture that can well suit the disparate patterns and distributions carried by the various datasets in a priori. Whereas many works in federated learning 1 and neural architecture search 2 have been proposed to address one of the two concerns, very few have attempted the both. To close the gap, in this paper we deliver a framework, termed Multi-Granular Federated Neural Architecture Search (MGFNAS), to enable the automation of model architecture search in a federated and thus privacy-preserved setting. We argue that our MGFNAS framework is general in the sense that it does not impose any restriction on the search space or strategy, such that most existing neural architecture search techniques can be readily implemented in. The main idea of our framework is to search the optimal neural network architecture in two levels of granularity, enabling the neural-operator-based micro-level search and the cell-based macro-level search. The main challenge of implementing our framework lies in the fact that, due to the decentralized nature, the local architectures searched by multiple clients can differ drastically in order to fit their own datasets, while a general method to form the global model by aggregating the local architectures in both micro and macro levels is missing. To solve the issue, we propose a novel aggregation function, named Network Architecture Probabilistic Aggregation (NAPA). The key idea of our NAPA function is to treat the network architectures as graphs, of which the sub-graph structures being frequently appeared across multiple clients are modeled by probabilistic distributions. At each round, a global model is formed by sampling from those distributions in an exploration-exploitation fashion. Extensive experiments are carried out, and the results substantiate the viability and effectiveness of our proposed framework.
To further enhance the reliability of Machine Learning (ML) systems, considerable efforts have been dedicated to developing privacy protection techniques. Recently, membership privacy has gained ...increasing attention, with a focus on determining whether a specific data point is present in the confidential training set of an ML model. However, most current attacks only prioritize attack accuracy and fail to extend their range to the evidence that contributes to the member/non-member classification. This limitation greatly reduces the practicality of Membership Inference Attacks (MIA), as real-world data typically includes multiple features, making it challenging to identify which features are involved in the sensitive training set. Therefore, this paper targets one of the fundamental challenges in membership inference attack: measuring the distance between an attack sample and a member sample. Specifically, we propose a novel threat model called Membership Reconstruction Attack (MRA), which aims to reconstruct the exact distribution of the target training set. MRA achieves this by marking each input dimension (e.g., pixels) according to its similarity to the target dataset in feature space. Our attack demonstrates its effectiveness across various settings, including different major datasets (MNIST, CIFAR-10, CIFAR-100) and different model architectures (AlexNet, ResNet, DenseNet, and generative models). Additionally, we evaluate MRA from the defenders' perspective and test several defense approaches against our attack.
PDF
