Each scanner possesses its unique characteristics and exhibits its distinct sampling error distribution. Training a network on a dataset that includes data collected from different scanners is less effective than trai...
详细信息
Network traffic occurring in the internet is a challenging issue due to the increase in internet users. Nowadays, internet traffic increases exponentially every month. Communication capability between the networks bec...
详细信息
Deepfake detection aims to mitigate the threat of manipulated content by identifying and exposing forgeries. However, previous methods primarily tend to perform poorly when confronted with cross-dataset scenarios. To ...
详细信息
Graphics Interchange Format (GIF) encoding is the art of reproducing an image with limited colors. Existing GIF encoding schemes often introduce unpleasant visual artifacts such as banding artifact, dotted-pattern noi...
详细信息
Ransomware is one of the most advanced malware which uses high computer resources and services to encrypt system data once it infects a system and causes large financial data losses to the organization and individuals...
详细信息
Digitization of healthcare data has shown an urgent necessity to deal with privacy concerns within the field of deep learning for healthcare organizations. A promising approach is federated transfer learning, enabling...
详细信息
Digitization of healthcare data has shown an urgent necessity to deal with privacy concerns within the field of deep learning for healthcare organizations. A promising approach is federated transfer learning, enabling medical institutions to train deep learning models collaboratively through sharing model parameters rather than raw data. The objective of this research is to improve the current privacy-preserving federated transfer learning systems that use medical data by implementing homomorphic encryption utilizing PYthon for Homomorphic Encryption Libraries (PYFHEL). The study leverages a federated transfer learning model to classify cardiac arrhythmia. The procedure begins by converting raw Electrocardiogram (ECG) scans into 2-D ECG images. Then, these images are split and fed into the local models for extracting features and complex patterns through a finetuned ResNet50V2 pre-trained model. Optimization techniques, including real-time augmentation and balancing, are also applied to maximize model performance. Deep learning models can be vulnerable to privacy attacks that aim to access sensitive data. By encrypting only model parameters, the Cheon-Kim-Kim-Song (CKKS) homomorphic scheme protects deep learning models from adversary attacks and prevents sensitive raw data sharing. The aggregator uses a secure federated averaging method that averages encrypted parameters to provide a global model protecting users’ privacy. The system achieved an accuracy rate of 84.49% when evaluated using the MIT-BIH arrhythmia dataset. Furthermore, other comprehensive performance metrics were computed to gain deeper insights, including a precision of 72.84%, recall of 51.88%, and an F1-score of 55.13%, reflecting a better understanding of the adopted framework. Our findings indicate that employing the CKKS encryption scheme in a federated environment with transfer cutting-edge technology achieves relatively high accuracy but at the cost of other performance metrics, which is lower
Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplor...
详细信息
Graph neural networks (GNNs) have gained increasing popularity, while usually suffering from unaffordable computations for real-world large-scale applications. Hence, pruning GNNs is of great need but largely unexplored. The recent work Unified GNN Sparsification (UGS) studies lottery ticket learning for GNNs, aiming to find a subset of model parameters and graph structures that can best maintain the GNN performance. However, it is tailed for the transductive setting, failing to generalize to unseen graphs, which are common in inductive tasks like graph classification. In this work, we propose a simple and effective learning paradigm, Inductive Co-Pruning of GNNs (ICPG), to endow graph lottery tickets with inductive pruning capacity. To prune the input graphs, we design a predictive model to generate importance scores for each edge based on the input. To prune the model parameters, it views the weight’s magnitude as their importance scores. Then we design an iterative co-pruning strategy to trim the graph edges and GNN weights based on their importance scores. Although it might be strikingly simple, ICPG surpasses the existing pruning method and can be universally applicable in both inductive and transductive learning settings. On 10 graph-classification and two node-classification benchmarks, ICPG achieves the same performance level with 14.26%–43.12% sparsity for graphs and 48.80%–91.41% sparsity for the GNN model.
The nonlinear filtering problem has enduringly been an active research topic in both academia and industry due to its ever-growing theoretical importance and practical *** main objective of nonlinear filtering is to i...
详细信息
The nonlinear filtering problem has enduringly been an active research topic in both academia and industry due to its ever-growing theoretical importance and practical *** main objective of nonlinear filtering is to infer the states of a nonlinear dynamical system of interest based on the available noisy measurements. In recent years, the advance of network communication technology has not only popularized the networked systems with apparent advantages in terms of installation,cost and maintenance, but also brought about a series of challenges to the design of nonlinear filtering algorithms, among which the communication constraint has been recognized as a dominating concern. In this context, a great number of investigations have been launched towards the networked nonlinear filtering problem with communication constraints, and many samplebased nonlinear filters have been developed to deal with the highly nonlinear and/or non-Gaussian scenarios. The aim of this paper is to provide a timely survey about the recent advances on the sample-based networked nonlinear filtering problem from the perspective of communication constraints. More specifically, we first review three important families of sample-based filtering methods known as the unscented Kalman filter, particle filter,and maximum correntropy filter. Then, the latest developments are surveyed with stress on the topics regarding incomplete/imperfect information, limited resources and cyber ***, several challenges and open problems are highlighted to shed some lights on the possible trends of future research in this realm.
The rapid rise of cyberattacks and the gradual failure of traditional defense systems and approaches led to using artificial intelligence (AI) techniques (such as machine learning (ML) and deep learning (DL)) to build...
详细信息
The rapid rise of cyberattacks and the gradual failure of traditional defense systems and approaches led to using artificial intelligence (AI) techniques (such as machine learning (ML) and deep learning (DL)) to build more efficient and reliable intrusion detection systems (IDSs). However, the advent of larger IDS datasets has negatively impacted the performance and computational complexity of AI-based IDSs. Many researchers used data preprocessing techniques such as feature selection and normalization to overcome such issues. While most of these researchers reported the success of these preprocessing techniques on a shallow level, very few studies have been performed on their effects on a wider scale. Furthermore, the performance of an IDS model is subject to not only the utilized preprocessing techniques but also the dataset and the ML/DL algorithm used, which most of the existing studies give little emphasis on. Thus, this study provides an in-depth analysis of feature selection and normalization effects on IDS models built using three IDS datasets: NSL-KDD, UNSW-NB15, and CSE–CIC–IDS2018, and various AI algorithms. A wrapper-based approach, which tends to give superior performance, and min-max normalization methods were used for feature selection and normalization, respectively. Numerous IDS models were implemented using the full and feature-selected copies of the datasets with and without normalization. The models were evaluated using popular evaluation metrics in IDS modeling, intra- and inter-model comparisons were performed between models and with state-of-the-art works. Random forest (RF) models performed better on NSL-KDD and UNSW-NB15 datasets with accuracies of 99.86% and 96.01%, respectively, whereas artificial neural network (ANN) achieved the best accuracy of 95.43% on the CSE–CIC–IDS2018 dataset. The RF models also achieved an excellent performance compared to recent works. The results show that normalization and feature selection positively affect I
As the use of big data and its potential benefits become more widespread, public and private organizations around the world have realized the imperative of incorporating comprehensive and robust technologies into thei...
详细信息
暂无评论