Multitask Learning for Security and Privacy in IoV (Internet of Vehicles)

Buttar, Ahmed Mateen; Sajja, Guna Sekhar; Gour, Sanjeev; Naved, Mohd; William, P.

doi:10.1002/9781119871989.ch12

Cited by 21 publications

(4 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…В другой работе, ориентированной на сетевые данные [10], была предложена гибридная модель MTL, использующая контрастное обучение (contrastive learning), кластеризацию и классификатор на основе многоуровневого восприятия (Multiple Layer Perception, MLP). С точки зрения конкретного применения в специальных средах IoT, способность MTL создавать одну унифицированную первичную модель для решения нескольких задач с использованием одного и того же набора данных позволяет хорошо адаптироваться и работать в динамических в распределенных системах с обширными объемами данных [11,12].…”

Section: релевантные работыunclassified

“…Функция преобразования выполняет SoftMax при умножении входного сигнала x и соответствующей обучаемой матрицы параметров. Когда имеется n сетей, реализованных в общем блоке, а W gt обозначает обучаемые веса, процесс вычисления распределения по множеству моделей и создания взвешенной суммы выходных данных всех моделей представляется с помощью (5): В WeightedBCE инициализация весов потерь рассчитывается на основе основных меток истинности y. Задавая отрицательную метку как ноль, а положительную метку как единицу, начальные веса, соответствующие отрицательным случаям ratio neg и положительным случаям ratio pos , вычисляются как (10) и (11): ratio neg = Σ(y) / len(y), (…”

Section: (а) (б) рисунок 3 механизмы жесткого и мягкого совместного и...unclassified

See 1 more Smart Citation

Detecting Attacks on the Internet of Things Based on Multitasking Learning and Hybrid Sampling Methods

2024

Cybersecurity Issues

View full text Add to dashboard Cite

The purpose of the study: To analyze and implement methods of multi-task learning and hybrid sampling of network traffic data to detect attacks in Internet of Things networks in order to improve the representation of minority classes and achieve data balance; compare the performance of various neural networks based on single-task and multi-task learning with hard and soft separation of parameters; implement weight optimization methods that provide automatic initialization and tuning of deep learning parameters for attack detection tasks in Internet of Things networks.Research methods: system analysis, modeling, deep machine learning.Results obtained: An approach to detecting attacks in Internet of Things networks based on multi-task learning is proposed. A comparison was made of the effectiveness of single-task learning models and multi-task learning models with hard and soft sharing of parameters. A hybrid sampling method is presented that combines random undersampling with oversampling based on a generative adversarial network. In addition, a weight initialization algorithm is implemented to eliminate imbalanced classification in IoT networks, ensuring high performance of the model for different classes of attacks represented in the dataset. Experiments were performed on different datasets, and the results showed that multi-task learning models outperform single-task learning for network traffic classification, achieving higher detection performance, especially for rare attacks.Scientific novelty: A new approach to detecting attacks in Internet of Things networks based on multi-task learning and hybrid sampling methods is proposed. An analysis and comparison of hard and soft parameter sharing in multi-task learning is carried out. The proposed approach aims to solve the problem of unbalanced traffic classification in IoT networks by random undersampling and synthetic sample generation using a pre-trained generative adversarial network model to achieve efficient data rebalancing.

show abstract

Section: релевантные работыunclassified

Section: (а) (б) рисунок 3 механизмы жесткого и мягкого совместного и...unclassified

Detecting Attacks on the Internet of Things Based on Multitasking Learning and Hybrid Sampling Methods

2024

Cybersecurity Issues

View full text Add to dashboard Cite

show abstract

“…Sensors, vehicles, tablets, wearable devices and more have joined the network, spawning a host of technologies and applications. For example, smart city, intelligent transportation [1], coastal monitoring [2], intelligent agriculture [3], augmented reality (AR)/virtual reality (VR), intelligent healthcare [4] and so on are developing rapidly. Global anytime and anywhere network access, large-scale machine-type communication and ultra-reliable low latency communication have become the development trend of the 6G network in the future [5].…”

Section: Introductionmentioning

confidence: 99%

Satellite-Air-Terrestrial Cloud Edge Collaborative Networks: Architecture, Multi-Node Task Processing and Computation

Liu,

Zhang,

Han

et al. 2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Integrated satellite-terrestrial network (ISTN) has been considered a novel network architecture to achieve global three-dimensional coverage and ultra-wide area broadband access anytime and anywhere. Being a promising paradigm, cloud computing and mobile edge computing (MEC) have been identified as key technology enablers for ISTN to further improve quality of service and business continuity. However, most of the existing ISTN studies based on cloud computing and MEC regard satellite networks as relay networks, ignoring the feasibility of directly deploying cloud computing nodes and edge computing nodes on satellites. In addition, most computing tasks are transferred to cloud servers or offloaded to nearby edge servers, the layered design of integrated satellite-air-terrestrial architecture and the cloudedge-device cooperative processing problems have not been fully considered. Therefore, different from previous works, this paper proposed a novel satelliteair-terrestrial layered architecture for cloud-edge-device collaboration, named SATCECN. Then this paper analyzes the appropriate deployment locations of cloud servers and edge servers in ISTN, and describes the processing flow of typical satellite computing tasks. For computing resource allocation problems, this paper proposed a device-edge-cloud Multi-node Cross-layer Collaboration Computing (MCCC) method to find the optimal task allocation strategy that minimizes the task completion delay and the weighted system energy consumption. Furthermore, the approximate optimal solutions of the optimization model are obtained by using successive convex approximation algorithm, and the outstanding advantages of the proposed method in reducing system energy consumption and task execution delay are verified through experiments. Finally, some potential issues and directions for future research are highlighted.

show abstract

“…Hong et al [2] mentioned that the involvement of data has raised concerns about the risks of secure data sharing, which becomes a huge challenge when deploying IoT applications into real applications. Mustafa et al [3] mentioned that the security of data is crucial in the Internet of Vehicles (IoV) and provided a comprehensive study of the application of artificial intelligence and machine learning on IoV network data to predict all potential threats to secure the IoV from various attacks and threats. Mustafa et al [4] mentioned that perceived security risk based on moderating factors for blockchain technology applications in cloud storage to achieve secure healthcare systems is important.…”

Section: Introductionmentioning

confidence: 99%

A Study on the Security of Online Judge System Applied Sandbox Technology

et al. 2023

View full text Add to dashboard Cite

The majority of programming courses currently employ online judge systems as lesson materials. Online judge systems are becoming more common as the number of courses and persons studying computer science and information engineering grows. At the same time, there is an increase in the number of attacks against online judge systems; for example, Denial-Of-Service attacks, whose goal is to disrupt the target system by exhausting resources and blocking ordinary users from using the service normally. As a result, preventing attacks on online judge systems is becoming increasingly crucial. This research investigates and organizes these attack techniques, as well as develops a threat model for the online judge system by the STRIDE threat model approach, which provides a way to classify attacks into six categories. This research also designs code analysis rules and implements a code analysis tool. This tool can assist developers in analyzing the existing online judge system to determine whether the judge system is vulnerable to attack and dealing with vulnerability as soon as feasible to improve the judge system’s security. After enhancing the security of online judge systems, the system can foster trust and reliability among users as benefits.

show abstract

Multitask Learning for Security and Privacy in IoV (Internet of Vehicles)

Cited by 21 publications

References 23 publications

Detecting Attacks on the Internet of Things Based on Multitasking Learning and Hybrid Sampling Methods

Detecting Attacks on the Internet of Things Based on Multitasking Learning and Hybrid Sampling Methods

Satellite-Air-Terrestrial Cloud Edge Collaborative Networks: Architecture, Multi-Node Task Processing and Computation

A Study on the Security of Online Judge System Applied Sandbox Technology

Contact Info

Product

Resources

About