Comprehensive Review on Facets of Cloud Computing in Context of Security and Privacy by Saurabh Aggarwal, Ashish Khanna, Abhilash Maroju

“…Cloud adoption is hampered by the serious security and privacy issues that arise when data and apps are outsourced to unaffiliated cloud providers. …”
Get full text

Voice Fence Wall: User-optional voice privacy transmission by Li Luo, Yining Liu

“…Sensors are widely applied in the collection of voice data. Since many attributes of voice data are sensitive such as user emotions, identity, raw voice collection may lead serious privacy threat. …”
Get full text

SpyKing—Privacy-preserving framework for Spiking Neural Networks by Farzad Nikfam, Alberto Marchisio, Maurizio Martina, Muhammad Shafique

“…However, the vast amount of data they process is not always secure, posing potential risks to privacy and safety. …”
Get full text

Differential privacy budget optimization based on deep learning in IoT by Dan LUO, Ruzhi XU, Zhitao GUAN

“…In order to effectively process the massive data brought by the large-scale application of the internet of things (IoT), deep learning is widely used in IoT environment.However, in the training process of deep learning, there are security threats such as reasoning attacks and model reverse attacks, which can lead to the leakage of the original data input to the model.Applying differential privacy to protect the training process parameters of the deep model is an effective way to solve this problem.A differential privacy budget optimization method was proposed based on deep learning in IoT, which adaptively allocates different budgets according to the iterative change of parameters.In order to avoid the excessive noise, a regularization term was introduced to constrain the disturbance term.Preventing the neural network from over fitting also helps to learn the salient features of the model.Experiments show that this method can effectively enhance the generalization ability of the model.As the number of iterations increases, the accuracy of the model trained after adding noise is almost the same as that obtained by training using the original data, which not only achieves privacy protection, but also guarantees the availability, which means balance the privacy and availability.…”
Get full text

Differential privacy budget optimization based on deep learning in IoT by Dan LUO, Ruzhi XU, Zhitao GUAN

“…In order to effectively process the massive data brought by the large-scale application of the internet of things (IoT), deep learning is widely used in IoT environment.However, in the training process of deep learning, there are security threats such as reasoning attacks and model reverse attacks, which can lead to the leakage of the original data input to the model.Applying differential privacy to protect the training process parameters of the deep model is an effective way to solve this problem.A differential privacy budget optimization method was proposed based on deep learning in IoT, which adaptively allocates different budgets according to the iterative change of parameters.In order to avoid the excessive noise, a regularization term was introduced to constrain the disturbance term.Preventing the neural network from over fitting also helps to learn the salient features of the model.Experiments show that this method can effectively enhance the generalization ability of the model.As the number of iterations increases, the accuracy of the model trained after adding noise is almost the same as that obtained by training using the original data, which not only achieves privacy protection, but also guarantees the availability, which means balance the privacy and availability.…”
Get full text

Scalable Distributed Reproduction Numbers of Network Epidemics With Differential Privacy by Bo Chen, Baike She, Calvin Hawkins, Philip E. Pare, Matthew T. Hale

“…Reproduction numbers are widely used to analyze epidemic spreading processes over networks. …”
Get full text

Towards edge-collaborative, lightweight and privacy-preserving classification framework by Jinbo XIONG, Yongjie ZHOU, Renwan BI, Liang WAN, Youliang TIAN

“…Aiming at the problems of data leakage of perceptual image and computational inefficiency of privacy-preserving classification framework in edge-side computing environment, a lightweight and privacy-preserving classification framework (PPCF) was proposed to supports encryption feature extraction and classification, and achieve the goal of data transmission and computing security under the collaborative classification process of edge nodes.Firstly, a series of secure computing protocols were designed based on additive secret sharing.Furthermore, two non-collusive edge servers were used to perform secure convolution, secure batch normalization, secure activation, secure pooling and other deep neural network computing layers to realize PPCF.Theoretical and security analysis indicate that PPCF has excellent accuracy and proved to be security.Actual performance evaluation show that PPCF can achieve the same classification accuracy as plaintext environment.At the same time, compared with homomorphic encryption and multi-round iterative calculation schemes, PPCF has obvious advantages in terms of computational cost and communication overhead.…”
Get full text

Privacy-preserving method for face recognition based on homomorphic encryption. by Zhigang Song, Gong Wang, Wenqin Yang, Yunliang Li, Yinsheng Yu, Zeli Wang, Xianghan Zheng, Yang Yang

“…Performance analysis indicates that the HE_FaceNet framework successfully protects facial data privacy while maintaining high recognition accuracy, and the optimization scheme demonstrates high accuracy and significant computational efficiency across facial datasets of varying sizes.…”
Get full text

GDPR-oriented intelligent checking method of privacy policies compliance by Xin LI, Peng TANG, Xiheng ZHANG, Weidong QIU, Hong HUI

“…The implementation of the EU’s General Data Protection Regulation (GDPR) has resulted in the imposition of over 300 fines since its inception in 2018.These fines include significant penalties for prominent companies like Google, which were penalized for their failure to provide transparent and comprehensible privacy policies.The GDPR, known as the strictest data protection laws in history, has made companies worldwide more cautious when offering cross-border services, particularly to the European Union.The regulation's territorial scope stipulates that it applies to any company providing services to EU citizens, irrespective of their location.This implies that companies worldwide, including domestic enterprises, are required to ensure compliance with GDPR in their privacy policies, especially those involved in international operations.To meet this requirement, an intelligent detection method was introduced.Machine learning and automation technologies were utilized to automatically extract privacy policies from online service companies.The policies were converted into a standardized format with a hierarchical structure.Through natural language processing, the privacy policies were classified, allowing for the identification of relevant GDPR concepts.In addition, a constructed GDPR taxonomy was used in the detection mechanism to identify any missing concepts as required by GDPR.This approach facilitated intelligent detection of GDPR-oriented privacy policy compliance, providing support to domestic enterprises while they provided cross-border services to EU users.Analysis of the corpus samples reveals the current situation that mainstream online service companies generally fail to meet GDPR compliance requirements.…”
Get full text

Balancing Security and Privacy: Web Bot Detection, Privacy Challenges, and Regulatory Compliance under the GDPR and AI Act [version 1; peer review: 2 approved] by Javier Martínez Llamas, Davy Preuveneers, Koen Vranckaert, Wouter Joosen

“…Additionally, the study dives into the use of Privacy Enhancing Technologies (PETs) to strike a balance between bot detection and user privacy. …”
Get full text

Privacy-Preserving Image Captioning with Partial Encryption and Deep Learning by Antoinette Deborah Martin, Inkyu Moon

“…In this study, a privacy-preserving image captioning framework that leverages partial encryption using Double Random Phase Encoding (DRPE) and deep learning is proposed to address privacy concerns. …”
Get full text

Efficient verifiable searchable encryption with search and access pattern privacy by Wu Axin, Feng Dengguo, Zhang Min, Chi Jialin, Zhang Yinghui

“…To address these concerns, we first design an efficient conjunctive SE scheme with search and access pattern privacy using private set intersection. In the proposed scheme, we utilize random numbers to obfuscate the values of polynomials and randomly divide the results into two parts, which simplifies the search process, improves search efficiency, and eliminates the need for time-consuming ciphertext multiplication operations. …”
Get full text

AI-Driven Optimization of Blockchain Scalability, Security, and Privacy Protection by Fujiang Yuan, Zihao Zuo, Yang Jiang, Wenzhou Shu, Zhen Tian, Chenxi Ye, Junye Yang, Zebing Mao, Xia Huang, Shaojie Gu, Yanhong Peng

“…With the continuous development of technology, blockchain has been widely used in various fields by virtue of its decentralization, data integrity, traceability, and anonymity. …”
Get full text

Dynamic and efficient vehicular cloud management scheme with privacy protection by Min XIAO, Tao YAO, Yuanni LIU, Yonghong HUANG

“…The vehicular cloud (VC) formed by vehicles is used for localization processing and consumption of traffic sensing data to achieve timely intelligent traffic management.The vehicle cloud is highly dynamic, self-organizing and timely, in which the identity and location privacy of vehicle users need to be protected as this poses challenges to the vehicular cloud management.A dynamic and self-organizing vehicle cloud management scheme based on the asymmetric group key agreement protocol was designed, where the vehicle cloud is automatically formed through the self-organized group key agreement of vehicles.The group key was used to control the provision and access of vehicle cloud services, and the dynamic management of the vehicle cloud was implemented through group key update.The scheme used traceable one-time pseudonym technology to achieve anonymous authentication and conditional privacy protection of vehicle users, and the group key agreement stage only included one bilinear pair operation to achieve high efficiency.In addition, the key negotiation and update process used lightweight signatures, supporting batch verification, to achieve efficient message source authentication and integrity authentication.Then the security and efficiency of vehicle cloud communications in the self-organizing environment can be ensured.The dynamic key update mechanism of the key agreement protocol realized the dynamic joining or exiting of vehicles in the vehicle cloud, adapting to the dynamic characteristics of the vehicle cloud.Under the random oracle model and the difficult assumption of the inverse computational Diffie Hellman (ICDH) problem, it was proved that the asymmetric group key agreement scheme satisfied the selective-plaintext security.The security analysis shows that the scheme can protect the identity and location privacy of vehicle users, realize the legal tracking of malicious vehicles, and ensure the confidentiality, integrity and anti-counterfeiting of communications, as well as the forward security of vehicle cloud dynamic management.The performance comparison analysis shows that this scheme has certain advantages in communication and computing efficiency under the condition of the same function and security level.…”
Get full text

Secured cloud-based image data processing of self-driving vehicles using full homomorphic encryption by Kamran Saeed, M.Fatih Adak

“…A novel method using full homomorphic encryption (FHE) image-based data is proposed, incorporating three different methods to search for the desired encrypted images stored in the cloud. …”
Get full text

Assessing the Fidelity and Utility of Water Systems Data Using Generative Adversarial Networks: A Technical Review by Md Nazmul Kabir Sikder, Yingjie Wang, Feras A. Batarseh

“…This review paper addresses this limitation by utilizing Generative Adversarial Networks (GANs) to generate realistic synthetic datasets, overcoming data scarcity and privacy concerns in WDSs. We review, train, and evaluate seven state-of-the-art GAN models using three multivariate time-series datasets. …”
Get full text

Travel Behavior during the 2021 British Columbia Floods Using De-identified Network Mobility Data by Enqi Liao, Syeda N. Zehra, Stephen D. Wong

“…This study investigates residents’ emergent travel behavior before, during, and after the 2021 British Columbia Floods. Using de-identified network mobility data, we analyze travel patterns centered around the municipality of Hope in British Columbia, Canada. …”
Get full text

Predicting Alzheimer's Disease onset: A machine learning framework for early diagnosis using biomarker data by Shehu Mohammed, Neha Malhotra

Get full text

AN APPROACH PRIORITIZING THE CAUSAL FACTORS OF LARGE SCALED DATA USING SOFT COMPUTING: A CASE STUDY by Jyoti Prakash MISHRA, Zdzislaw POLKOWSKI, Sambit Kumar MISHRA

Get full text

A comprehensive review of methodologies and application to use the real-world data and analytics platform TriNetX by Ralf J. Ludwig, Ralf J. Ludwig, Ralf J. Ludwig, Matthew Anson, Matthew Anson, Henner Zirpel, Diamant Thaci, Henning Olbrich, Katja Bieber, Khalaf Kridin, Khalaf Kridin, Khalaf Kridin, Astrid Dempfle, Philip Curman, Philip Curman, Philip Curman, Philip Curman, Sizheng S. Zhao, Uazman Alam, Uazman Alam, Uazman Alam

Get full text