The Internet of Things (IOT) connects Tangible assets via data fusion facilitating information interchange. Ranging from basic temperature sensors to sophisticated industrial robots, IOT covers a wide range of applica...
详细信息
In this paper, we build neural-network model-based automatic speech recognition (ASR) systems incrementally for performance improvement. First, we add an adversarial text discriminator module to train the speech recog...
详细信息
The ever-expanding Internet of Things (IoT) landscape presents a double-edged sword. While it fosters interconnectedness, the vast amount of data generated by IoT devices creates a larger attack surface for cybercrimi...
详细信息
The ever-expanding Internet of Things (IoT) landscape presents a double-edged sword. While it fosters interconnectedness, the vast amount of data generated by IoT devices creates a larger attack surface for cybercriminals. Intrusions in these environments can have severe consequences. To combat this growing threat, robust intrusion detection systems (IDS) are crucial. The data comprised by this attack is multivariate, highly complex, non-stationary, and nonlinear. To extract the complex patterns from this complex data, we require the most robust, optimized tools. Machine learning (ML) and deep learning (DL) have emerged as powerful tools for IDSs, offering high accuracy in detecting and preventing security breaches. This research delves into anomaly detection, a technique that identifies deviations from normal system behavior, potentially indicating attacks. Given the complexity of anomaly data, we explore methods to improve detection performance. This research investigates the design and evaluation of a novel IDS. We leverage and optimize supervised ML methods like tree-based Support Vector Machines (SVM), ensemble methods, and neural networks (NN) alongside the cutting-edge DL approach of long short-term memory (LSTM) and vision transformers (ViT). We optimized the hyperparameters of these algorithms using a robust Bayesian optimization approach. The implemented ML models achieved impressive training accuracy, with Random Forest and Ensemble Bagged Tree surpassing 99.90% of accuracy, an AUC of 1.00, an F1-score, and a balanced Matthews Correlation Coefficient (MCC) of 99.78%. While the initial deep learning LSTM model yielded an accuracy of 99.97%, the proposed ViT architecture significantly boosted performance with 100% of all metrics, along with a validation accuracy of 78.70% and perfect training accuracy. This study demonstrates the power of our new methods for detecting and stopping attacks on Internet of Things (IoT) networks. This improved detection offers
This article addresses the scheduling problem of coflows in identical parallel networks, a well-known NPNP-hard problem. We consider both flow-level scheduling and coflow-level scheduling problems. In the flow-level s...
详细信息
With the increasing number of edited videos, many robust video fingerprinting schemes have been proposed to solve the problem of video content authentication. However, most of them either deal with the temporal and sp...
详细信息
As a significant application of machine learning in financial scenarios, loan default risk prediction aims to evaluate the client’s default probability. However, most existing deep learning solutions treat each appli...
详细信息
In the domain of Very-Large-Scale Integration (VLSI) design, the accuracy of pre-routing timing prediction is of paramount importance for ensuring the performance and reliability of integrated circuits. Traditional me...
详细信息
Federated recommender systems(FedRecs) have garnered increasing attention recently, thanks to their privacypreserving benefits. However, the decentralized and open characteristics of current FedRecs present at least t...
详细信息
Federated recommender systems(FedRecs) have garnered increasing attention recently, thanks to their privacypreserving benefits. However, the decentralized and open characteristics of current FedRecs present at least two ***, the performance of FedRecs is compromised due to highly sparse on-device data for each client. Second, the system's robustness is undermined by the vulnerability to model poisoning attacks launched by malicious users. In this paper, we introduce a novel contrastive learning framework designed to fully leverage the client's sparse data through embedding augmentation, referred to as CL4FedRec. Unlike previous contrastive learning approaches in FedRecs that necessitate clients to share their private parameters, our CL4FedRec aligns with the basic FedRec learning protocol, ensuring compatibility with most existing FedRec implementations. We then evaluate the robustness of FedRecs equipped with CL4FedRec by subjecting it to several state-of-the-art model poisoning attacks. Surprisingly, our observations reveal that contrastive learning tends to exacerbate the vulnerability of FedRecs to these attacks. This is attributed to the enhanced embedding uniformity, making the polluted target item embedding easily proximate to popular items. Based on this insight, we propose an enhanced and robust version of CL4FedRec(rCL4FedRec) by introducing a regularizer to maintain the distance among item embeddings with different popularity levels. Extensive experiments conducted on four commonly used recommendation datasets demonstrate that rCL4FedRec significantly enhances both the model's performance and the robustness of FedRecs.
Action recognition in videos is a critical task in computer vision, with a wide range of applications including security surveillance, behavior analysis, and cooperative control. Despite significant advancements in ac...
详细信息
Background: The most important aspect of medical image processing and analysis is image segmentation. Fundamentally, the outcomes of segmentation have an impact on all subsequent image testing methods, including objec...
详细信息
暂无评论