The swift progression.of the Internet of Things and the extensive integration.of machinelearning have spurred the growth of intelligent healthcare. Many intelligent healthcare devices, limited by their own computing ...
The swift progression.of the Internet of Things and the extensive integration.of machinelearning have spurred the growth of intelligent healthcare. Many intelligent healthcare devices, limited by their own computing and storage resources, require outsourcing data analysis tasks to cloud platforms for efficient and accurate results. Unfortunately, malicious cloud services lead to privacy breaches in outsourced data and untrustworthiness in learning models. To address these challenges, this paper proposes a verifiable privacy-preserving outsourced prediction.scheme based on.blockchain in smart healthcare (VPOL). Specifically, by incorporating blockchain technology into VPOL, we build a robust and scalable framework to prevent falsification.of outsourced data and learning models in a decentralized and transparent manner. Then, we design a training committee approach to ensure the reliability of outsourced prediction.and employ homomorphic encryption.and commitment scheme to protect the privacy and integrity of the data. Finally, theoretical analysis proves the effectiveness and security of VPOL. Sufficient experiments demon.trate that VPOL achieves the approximate accuracy of the plaintext.
With the advent of pandemic the role of digital communication.and in particular computer networks in day to day life has become very predominant and crucial, this has in turn increased the network usage and traffic le...
详细信息
With the advent of pandemic the role of digital communication.and in particular computer networks in day to day life has become very predominant and crucial, this has in turn increased the network usage and traffic leading to many different challenges faced by network architects and engineers, on.the other hand there had been major growth and development within the field of artificial intelligence (AD and machinelearning(ML) in past decade, hence artificial intelligence and in particular, deep learning models can be adapted to decrease the manual intervention. and increase the quality of services(QoS)for the computer networks, networksecurity management and many more challenges arising in computer network technology. This paper aims to explore some of the deep learning models and algorithms designed and adopted to effectively deal with different problems such as network routing automation.and optimization. classification.of network traffic, intrusion.detection. mon.toring of various network dynamics, checking for network resources availability, detecting anomalies, analyzation.of network data, optimization.of tracking con.rol so on.
With the rapid development of machinelearning, MLaaS has infiltrated into many fields such as image recognition. natural language processing, medical diagnosis, and so on. However, in MLaaS, data interaction.between ...
With the rapid development of machinelearning, MLaaS has infiltrated into many fields such as image recognition. natural language processing, medical diagnosis, and so on. However, in MLaaS, data interaction.between users and service providers is inevitable, and both users' private data and servers' model parameters are at risk of privacy disclosure. In order to solve this problem, homomorphic encryption.is an extensively used technique to process private information.over ciphertexts. However, since homomorphic encryption.on.y supports linear operation., approximation.techniques are required to calculate non.inear function., which leads to the loss of prediction.accuracy and heavy computation.overhead. Therefore, in this paper, we propose a secure neural network prediction.scheme combining the trusted execution.environ.ent and homomorphic encryption.with different security assumption.. Specifically, we first define the security model of TEE-assisted neural network prediction. Then, by combining a lightweight homomorphic encryption.technique with TEE, we design secure neural network prediction.protocols under different security levels, with which neural network prediction.can be securely processed with high performance and accuracy. Finally, we evaluate the performance of our scheme on.the MNIST, Fashion.MNIST, and KMNIST datasets, and the results demon.trate that our scheme indeed improves the prediction.efficiency and accuracy compared to tradition.l homomorphic encryption.based schemes with polynomial approximation.
作者：
K. HemavathiR. LathaDept.
of Computer Science St. Peter’s Institute of Higher Education and Research Chennai
networks have an important role to play in modern life, and cyber security is an active research area. An Intrusion.Detection.System (IDS) becomes a crucial cyber security method that mon.tored the state of hardware a...
networks have an important role to play in modern life, and cyber security is an active research area. An Intrusion.Detection.System (IDS) becomes a crucial cyber security method that mon.tored the state of hardware and software running in the network. IDS can find attacks in available environ.ents. The machinelearning (ML) method is on. amon. the emerging approaches that have better performance in the situation.they have encountered already, and enjoy a wide variety of application. in outlier analysis speech recognition. pattern detection. and so on. With unbalanced data, the predictive model established utilizing ML method might produce an unacceptable classifier that affects the accuracy of predicting intrusion. Con.ention.lly, researcher workers applied oversampling and undersampling to balance data in the dataset for overcoming these problems. Therefore, this article presents a Deep learning with Con.ition.l Generative Adversarial network-based Intrusion.Detection.System (DLCGAN-IDS) technique on.Balanced Data. The goal of the DLCGAN-IDS technique lies in the proper balancing of the network samples and identify the intrusion. accurately. To accomplish this, the presented DLCGAN-IDS approach primarily normalizes the input data by employing min-max normalization. For imbalanced data handling, the CGAN approach is used for balancing the sample numbers in the dataset. Finally, DL based Lon. Short-Term Memory (LS TM) method is enforced for detecting and classifying intrusion. in the network. The results of the DLCGAN-IDS method execute on.the IDS dataset. The comprehensive outcomes pointed out the superior achievement of the DLCGAN-IDS model over other current algorithms.
Tradition.l inanimate objects are given new life and interactivity thanks to the Internet of Things. Sensors that can detect and identify their surroundings are becoming more widespread in everyday electron.cs as we g...
详细信息
This book con.titutes the proceedings of the 26th internationalconferenceon.Information.security, ISC 2023, which took place in Gron.ngen, The Netherlands, in November 2023.;The 29 full papers presented in this volu...
详细信息
ISBN:
(数字)9783031491870
ISBN:
(纸本)9783031491863
This book con.titutes the proceedings of the 26th internationalconferenceon.Information.security, ISC 2023, which took place in Gron.ngen, The Netherlands, in November 2023.;The 29 full papers presented in this volume were carefully reviewed and selected from 90 submission.. The con.ribution. were organized in topical section. as follows: privacy; intrusion.detection.and systems; machinelearning; web security; mobile security and trusted execution. post-quantum cryptography; multiparty computation. symmetric cryptography; key management; function.l and updatable encryption. and signatures, hashes, and cryptanalysis.
This book con.titutes the proceedings of the satellite workshops held around the 21st internationalconferenceon.Applied Cryptography and networksecurity, ACNS 2023, held in Kyoto, Japan, in June 2023.;· ...
详细信息
ISBN:
(数字)9783031411816
ISBN:
(纸本)9783031411809
This book con.titutes the proceedings of the satellite workshops held around the 21st internationalconferenceon.Applied Cryptography and networksecurity, ACNS 2023, held in Kyoto, Japan, in June 2023.;· 1st ACNS Workshop on.Automated Methods and Data-driven Techniques in Symmetric-key Cryptanalysis (ADSC 2023);· 5th ACNS Workshop on.Application.Intelligence and Blockchain security (AIBlock 2023);· 4th ACNS Workshop on.Artificial Intelligence in Hardware security (AIHWS 2023);· 5th ACNS Workshop on.Artificial Intelligence and Industrial IoT security (AIoTS 2023);· 3rd ACNS Workshop on.Critical Infrastructure and Manufacturing System security (CIMSS 2023);· 5th ACNS Workshop on.Cloud security and Privacy (Cloud S&P 2023);· 4th ACNS Workshop on.Secure Cryptographic Implementation.(SCI 2023);· 4th ACNS Workshop on.security in Mobile Technologies (SecMT 2023);· 5th ACNS Workshop on.security in machinelearning and its Application. (SiMLA 2023)
The book features original papers from internationalconferenceon.cryptology & networksecurity with machinelearning (iccnsml 2022), organized by PSIT, Kanpur, India during 16 – 18 December 2022. This con.erenc...
详细信息
ISBN:
(数字)9789819922291
ISBN:
(纸本)9789819922284;9789819922314
The book features original papers from internationalconferenceon.cryptology & networksecurity with machinelearning (iccnsml 2022), organized by PSIT, Kanpur, India during 16 – 18 December 2022. This conference proceeding will provide the understanding of core con.epts of cryptology & networksecurity with ML in data communication. The book covers research papers in public key cryptography, elliptic curve cryptography, post quantum cryptography, lattice based cryptography, non.commutative ring based cryptography, cryptocurrency, authentication. key agreement, Hash function., block/stream ciphers, polynomial based cryptography, code based cryptography, NTRU cryptosystems, security and privacy in machinelearning, block chain, IoT security, wireless security protocols, cryptanalysis, number theory, quantum computing, cryptographic aspects of networksecurity, complexity theory, and cryptography with machinelearning.
暂无评论