Encrypted Data Processing Research Articles

Analyzing Machine Learning Models for Activity Recognition Using Homomorphically Encrypted Real-World Smart Home Datasets: A Case Study

The era of digitization and IoT devices is marked by the constant storage of massive amounts of data. The growing adoption of smart home environments, which use sensors and devices to monitor and control various aspects of daily life, underscores the need for effective privacy and security measures. HE is a technology that enables computations on encrypted data, preserving confidentiality. As a result, researchers have developed methodologies to protect user information, and HE is one of the technologies that make it possible to perform computations directly on encrypted data and produce results using this encrypted information. Thus, this research study compares the performance of three ML models, XGBoost, Random Forest, and Decision Classifier, on a real-world smart home dataset using both with and without FHE. Practical results demonstrate that the Decision Classifier showed remarkable results, maintaining high accuracy with FHE and even surpassing its plaintext performance, suggesting that encryption can enhance model accuracy under certain conditions. Additionally, Random Forest showed efficiency in terms of execution time and low prediction errors with FHE, making it a strong candidate for encrypted data processing in smart homes. These findings highlight the potential of FHE to set new privacy standards, advancing secure and privacy-preserving technologies in smart environments.

Сравнительный анализ методов построения систем обработки зашифрованных данных и их сравнение для решения задач машинного обучения

The article discusses two methods for constructing encrypted data processing systems based on homomorphic encryption and separation calculations. Each method differs from each other in the presented algorithm and data processing model. Basic operations on encrypted data are considered, namely, multiplication and addition. The following libraries were used for the study: tenSEAL, tensorflow and PyTorch. The tenSEAL library is a fork of the full homomorphic encryption tool created for the C++ programming language, but adapted for the Python programming language used in the study. This library allows you to use the method of full homomorphic encryption in constructing a computational model, the task of which will be to process encrypted data. To implement the method of separation calculations, better known as multi-party computation, the tensorflow library will be used, which allows you to create several tensors and train them simultaneously, which in turn makes it possible to implement the principle of separation calculations.

Real-time privacy-preserved auditing for shared outsourced data

Health providers need to share patient information across healthcare networks efficiently and securely to improve medical and health services. Timely data synchronization among relevant parties is crucial for effectively containing and preventing the worsening of the condition. However, ensuring rapid information sharing while maintaining the security of sensitive patient data remains a pressing concern. In this paper, we introduce a cloud storage integrity auditing scheme that can protect auditors from procrastinating and preserve the privacy of sensitive information. Our proposed system requires healthcare institutions to encrypt sensitive patient data before uploading it to the cloud. It mandates the use of a data sanitizer for the secure processing of encrypted data blocks. Auditors must verify data integrity and promptly submit their audit results to the blockchain within a predefined time frame. Leveraging the time-sensitive nature of blockchain technology, healthcare institutions can monitor auditor compliance within the allotted validation timeframe. We conducted comprehensive security analysis and performance evaluations to demonstrate the feasibility and effectiveness of our solution in addressing the challenges of secure and timely cloud storage in healthcare settings.

Recent advances of Privacy-Preserving Machine Learning based on (Fully) Homomorphic Encryption

Fully Homomorphic Encryption (FHE), known for its ability to process encrypted data without decryption, is a promising technique in solving the privacy concerns in the machine learning era. However, there are many kinds of available FHE schemes and way more FHE-based solutions in the literature, and they are still fast evolving, making it difficult to get a complete view. This article aims to introduce recent representative results of FHE-based privacy-preserving machine learning, helping users understand the pros and cons of different kind of solutions, and choose an appropriate approach for their needs.

IMPLEMENTATION OF AES AND SHA-3 CRYPTOGRAPHY ALGORITHMS IN SECURING USER SENSITIVE DATA ON THE ARTESIAN WATER BILL PAYMENT TRANSACTION WEBSITE

Transacting online is something that is familiar to almost everyone in the digital era. The presence of digital transactions brings convenience in carrying out trading activities, but the use of the internet in creating easy transactions with several challenges in the form of hacking. In order to realize secure transactions, the level of protection on digital transaction service provider sites must be made as strong as possible to prevent digital attacks. Therefore, a protection system for user payment data on one of the transaction websites was created by applying the AES and SHA-3 cryptographic algorithm methods. The AES algorithm method was chosen because its implementation is not complicated but has proven its security, while SHA-3 is used to create unique keys from user passwords with the latest hash technology, so that the data encryption and decryption process becomes more protected because it uses the secret key of each user but not directly. The application of cryptographic algorithms will provide additional protection for the security of nominal user transaction data from cyber attacks so that the data. This research will produce a cryptography program flow with the Python programming language and examples of encryption and hash process results during program execution.

Self-balancing Incremental Broad Learning System with privacy protection

Incremental learning algorithms have been developed as an efficient solution for fast remodeling in Broad Learning Systems (BLS) without a retraining process. Even though the structure and performance of broad learning are gradually showing superiority, private data leakage in broad learning systems is still a problem that needs to be solved. Recently, Multiparty Secure Broad Learning System (MSBLS) is proposed to allow two clients to participate training. However, privacy-preserving broad learning across multiple clients has received limited attention. In this paper, we propose a Self-Balancing Incremental Broad Learning System (SIBLS) with privacy protection by considering the effect of different data sample sizes from clients, which allows multiple clients to be involved in the incremental learning. Specifically, we design a client selection strategy to select two clients in each round by reducing the gap in the number of data samples in the incremental updating process. To ensure the security under the participation of multiple clients, we introduce a mediator in the data encryption and feature mapping process. Three classical datasets are used to validate the effectiveness of our proposed SIBLS, including MNIST, Fashion and NORB datasets. Experimental results show that our proposed SIBLS can have comparable performance with MSBLS while achieving better performance than federated learning in terms of accuracy and running time.

Comparative Analysis of AES, Blowfish, Twofish, Salsa20, and ChaCha20 for Image Encryption

Nowadays, cybersecurity has grown into a more significant and difficult sci-entific issue. The recognition of threats and attacks meant for knowledge and safety on the internet is growing harder to detect. Since cybersecurity guar-antees the privacy and security of data sent via the Internet, it is essential, while also providing protection against malicious attacks. Encrypt has grown into an answer that has become an essential element of information security systems. To ensure the security of shared data, including text, images, or videos, it is essential to employ various methods and strategies. This study delves into the prevalent cryptographic methods and algorithms utilized for prevention and stream encryption, examining their encoding techniques such as advanced encryption standard (AES), Blowfish, Twofish, Salsa20, and ChaCha20. The primary objective of this research is to identify the optimal times and throughputs (speeds) for data encryption and decryption processes. The methodology of this study involved selecting five distinct types of images to compare the outcomes of the techniques evaluated in this research. The as-sessment focused on processing time and speed parameters, examining visual encoding and decoding using Java as the primary platform. A comparative analysis of several symmetric key ciphers was performed, focusing on handling large datasets. Despite this limitation, comparing different images helped evaluate the techniques' novelty. The results showed that ChaCha20 had the best average time for both encryption and decryption, being over 50% faster than some other algorithms. However, the Twofish algorithm had lower throughput during testing. The paper concludes with findings and suggestions for future improvements.

MemFHE: End-to-end Computing with Fully Homomorphic Encryption in Memory

The increasing amount of data and the growing complexity of problems have resulted in an ever-growing reliance on cloud computing. However, many applications, most notably in healthcare, finance, or defense, demand security and privacy, which today’s solutions cannot fully address. Fully homomorphic encryption (FHE) elevates the bar of today’s solutions by adding confidentiality of data during processing. It allows computation on fully encrypted data without the need for decryption, thus fully preserving privacy. To enable processing encrypted data at usable levels of classic security, e.g., 128-bit, the encryption procedure introduces noticeable data size expansion—the ciphertext is much bigger than the native aggregate of native data types. In this article, we present MemFHE, which is the first accelerator of both client and server for the latest Ring-GSW (Gentry et al. [ 17 ])-based homomorphic encryption schemes using Processing in Memory (PIM). PIM alleviates the data movement issues with large FHE encrypted data while providing in situ execution and extensive parallelism needed for FHE’s polynomial operations. While the client-PIM can homomorphically encrypt and decrypt data, the server-PIM can process homomorphically encrypted data without decryption. MemFHE’s server-PIM is pipelined and is designed to provide flexible bootstrapping, allowing two encryption techniques and various FHE security levels based on the application requirements. We evaluate MemFHE for various security levels and compare it with state-of-the-art CPU implementations for Ring-GSW-based FHE. MemFHE is up to 20 k × (265×) faster than CPU (GPU) for FHE arithmetic operations and provides on average 2,007× higher throughput than [ 36 ] while implementing neural networks with FHE.

Advanced Authentication and Energy-Efficient Routing Protocol for Wireless Body Area Networks

Recently, wireless body area network (WBAN) becomes a hot research topic in the advanced healthcare system. The WBAN plays a vital role in monitoring the physiological parameters of the human body with sensors. The sensors are small in size, and it has a small-sized battery with limited life. Hence, the energy is limited in the multi-hop routing process. The patient data is collected by the sensor, and the data are transmitted with high energy consumption. It causes failure in the data transmission path. To avoid this, the data transmission process should be optimized. This paper presents an advanced authentication and energy-efficient routing protocol (AAERP) for optimal routing paths in WBAN. Patients’ data are aggregated from the WBAN through the IoMT devices in the initial stage. To secure the patient’s private data, a hybrid mechanism of the elliptic curve cryptosystem (ECC) and Paillier cryptosystem is proposed for the data encryption process. Data security is improved by authenticating the data before transmission using an encryption algorithm. Before the routing process, the data encryption approach converts the original plain text data into ciphertext data. This encryption approach assists in avoiding intrusions in the network system. The encrypted data are optimally routed with the help of the teamwork optimization algorithm (TOA) approach. The optimal path selection using this optimization technique improves the effectiveness and robustness of the system. The experimental setup is performed by using Python software. The efficacy of the proposed model is evaluated by solving parameters like network lifetime, network throughput, residual energy, success rate, number of packets received, number of packets sent, and number of packets dropped. The performance of the proposed model is measured by comparing the obtained results with several existing models.

A Realizable Data Encryption Strategy

As technology continues to advance, data has become an increasingly important element in the sphere of Information Technology. However, enormous data generated by devices presents a major challenge in handling it in real time. Data encryption is a crucial component in ensuring data security and privacy during its transmission in network. Unfortunately, many applications disregard data encryption in order to achieve higher performance. The work proposes a solution to this problem by introducing a data encryption process that is, the Realizable Data Encryption Strategy (RDES) and Deoxyribonucleic Acid (DNA) computing, a revolutionary cryptographic method that improves information security by preventing authorized access to sensitive data, being used. Information security is improved by DNA symmetric cryptography being suggested. The outcomes show that plain-text encryption is a very secure procedure. The RDES approach is designed to improve privacy protection within the constraints of real-time processing. By implementing the RDES approach, data privacy and security can be significantly enhanced without compromising performance.

BGNBA-OCO based privacy preserving attribute based access control with data duplication for secure storage in cloud

Cloud computing technology offers flexible and expedient services that carry a variety of profits for both societies as well as individuals. De-duplication techniques were developed to minimize redundant data in the cloud storage. But, one of the main challenges of cloud storage is data deduplication with secure data storage.To overcome the issue, we propose Boneh Goh Nissim Bilinear Attribute-based Optimal Cache Oblivious (BGNBA-OCO) access control and secure de-duplication for data storage in cloud computing in this paper. The proposed method achieves fne-grained access control with low computation consumption. We design Boneh Goh Nissim Privacy Preserving Revocable Attribute-based Encryption that reinforces attribute revocation and averts the discharge of sensitive information. Furthermore, we utilize Optimal Cache Oblivious algorithm to prevent disclosure of access patterns to hide the access patterns in cloud storage via rand pattern matching. We support updating both encrypted data and access control policies to minimize communication and computation overhead of data duplication and encryption processes concurrently. We perform secure data sharing to achieve higher data confidentiality and integrity. Finally, we conducted the extensive experiments in cloud and the results illustrated that our proposed BGNBA-OCO method is more efficient than related works.

Chebyshev polynomial approximation in CNN for zero-knowledge encrypted data analysis

Integrating Deep Learning (DL) techniques in Convolutional Neural Networks (CNNs) with encrypted data analysis is an emerging field for enhancing data privacy and security. A significant challenge in this domain is the incompatibility of standard non-linear Activation Functions (AF) like Rectified Linear Unit (ReLU) and Hyperbolic Tangent (tanh) with Zero-Knowledge (ZK) encrypted data, which impacts computational efficiency and data privacy. Addressing this, our paper introduces the novel application of Chebyshev Polynomial Approximation (CPA) to adapt these AF to process encrypted data effectively. Utilizing the MNIST dataset, this paper conducted experiments with LeNet and various configurations of AlexNet, extending the range of the ReLU and tanH functions to optimize CPA. Our results reveal an optimal polynomial degree (α), with α = 10 for ReLU and between α = 10 and α = 15 for tanH, beyond which the benefits in accuracy plateau. This finding is crucial for ensuring the accuracy and efficiency of CNNs in processing encrypted data. This recommended study demonstrates that while the accuracy slightly decreases for plaintext data and more significantly for ciphertext data, the overall effectiveness of CPA in CNNs is maintained. This advancement enables CNNs to process encrypted data while preserving privacy and marks a significant step in developing privacy-preserving Machine Learning (ML) and encrypted data analysis.

Aplikasi Pengamanan Data Karyawan menggunakan Algoritma Advanced Encryption Standard dan Cloud Computing berbasis Mobile

Documents are valuable assets that often contain important information, including employee personal data, and are vulnerable to security threats such as theft and alteration by unauthorized parties. This research aims to develop an Android-based document security application that combines the Advanced Encryption Standard (AES) algorithm and cloud computing technology. This type of research is developed using the System Development Life Cycle (SDLC) model, which involves requirements analysis, design, coding, and testing. At the needs analysis stage, focus is given to employee data that needs to be secured. System design includes data structure, system structure, and user interface (UI). System design includes use case elements, class diagrams, and application architecture. Coding was done using Flutter as the user interface, Laravel as the backend, and MySQL as the database. System testing uses black box testing. Our test results show that the data security application is successful in carrying out the data encryption and decryption processes. Compared to previous web and desktop-based developments, this application provides a more adaptive solution to high mobility in the work environment. Cloud computing integration provides flexibility in data access, and the use of the Android platform significantly increases user mobility.

Lightweight Cryptography based Communication Model for Device Identification, Mutual Authentication, and Encryption in a Smart City Environment

Providing security to smart city networks is one of the challenging and demanding tasks in the present days, due to its increased utilization in smart intelligent transportation systems. For this purpose, there are various security protocols and mechanisms that have been developed in the existing works, which targets to establish the reliable and secured communication in smart city networks. However, it limits the major issues of increased computational cost, communication cost, storage overhead, and reduced efficiency. In order to solve these problems, the proposed work intends to design an intelligent security framework by using the Light-weight Cryptography based Communication Model (LCCM). Proposed framework includes the modules of setup initialization, vehicle registration, authentication, key generation, encryption, and decryption. Here, the Vehicle-to-Vehicle (V2V) and Vehicle-to-Infrastructure (V2I) communications are performed with reduced cost complexity. For guaranteeing the security of networks, the random value-based key generation, data encryption, and decryption processes are performed. During the performance analysis, various evaluation measures have been used to assess the results of both convention and proposed security protocols. This paper presented a new methodology named as, LCCM for enhancing the security of smart city transportation networks.

Hybrid Encryption of Cloud Processing With IOT Devices Using DNA And RSA Cryptography

The research paper titled "Hybrid Data Encryption as well as Decryption Using Hybrid RSA and DNA" develops a hybrid cryptosystem by combining the usefulness of such an asymmetric-key (public-key) cryptosystem with the efficacy of a symmetric-key (private-key) cryptosystem. These two types of cryptosystems use different types of keys. The method addresses concerns regarding the users' right to privacy, authentication, and accuracy by utilizing a data encryption process that is secure in both directions. Both the process of encrypting data and the process of decrypting data, which are both utilized by the system, are two different encryption methods. It has been suggested that a hybrid encryption algorithm, which combines DNA and RSA, be used for file encryption in order to address the issues with efficiency and security. The results of the testing show that the RSA and DNA hybrid encryption algorithm is suitable for use. In this particular research project's hybrid encryption and decoding for cloud processing with IOT devices, the DNA and RSA algorithms were used.

Homomorphic additive lightweight block cipher scheme for securing IoT applications

Recent emerging systems and applications may be able to process encrypted data to preserve user privacy. However, designing an efficient Homomorphic Encryption (HE) algorithm that can achieve good performance and robustness against attacks is primordial to better respond to real-time requirements and tiny devices. Unfortunately, existing homomorphic asymmetric schemes suffer from high computational complexity, storage, and communication overhead. On the other hand, homomorphic symmetric approaches suffer from a low level of security, and a big majority of them suffer from weaknesses in defending against known plain-text/cipher-text attacks. In this paper, an efficient symmetric homomorphic block cipher scheme is proposed to allow the performing of addition and average operations over cipher-texts. It defines a simple round function that should be iterated for nr≥2 iterations. Moreover, the dynamic key approach is used in this solution to reach a high level of security. To the best of our knowledge, it is a new symmetric additive homomorphic block cipher structure, and it defines three novel variants of addition round keys and two novel variants of the diffusion matrix. Furthermore, the proposed solution is analyzed in detail and evaluated in terms of security and performance levels. In comparison with well-known asymmetric additive HE schemes such as Paillier, BGN (Boneh, Goh, Nissim), BCP (Bresson, Catalano, Pointcheval), and ElGamal ECC (Elliptic Curve ), the obtained results prove that the proposed solution reaches a good balance between both performance and security levels. Therefore, the proposed solution can be applied on limited devices and especially for real-time scenarios that require the additive homomorphic property and the average calculation over cipher-texts.

A Comparative Study of Secure Outsourced Matrix Multiplication Based on Homomorphic Encryption

Homomorphic encryption (HE) is a promising solution for handling sensitive data in semi-trusted third-party computing environments, as it enables processing of encrypted data. However, applying sophisticated techniques such as machine learning, statistics, and image processing to encrypted data remains a challenge. The computational complexity of some encrypted operations can significantly increase processing time. In this paper, we focus on the analysis of two state-of-the-art HE matrix multiplication algorithms with the best time and space complexities. We show how their performance depends on the libraries and the execution context, considering the standard Cheon–Kim–Kim–Song (CKKS) HE scheme with fixed-point numbers based on the Microsoft SEAL and PALISADE libraries. We show that Windows OS for the SEAL library and Linux OS for the PALISADE library are the best options. In general, PALISADE-Linux outperforms PALISADE-Windows, SEAL-Linux, and SEAL-Windows by 1.28, 1.59, and 1.67 times on average for different matrix sizes, respectively. We derive high-precision extrapolation formulas to estimate the processing time of HE multiplication of larger matrices.

An efficient integrity based multi-user blockchain framework for heterogeneous supply chain management applications

Most of the traditional cloud-based applications are insecure and difficult to compute the data integrity with variable hash size on heterogeneous supply chain datasets. Also, cloud storage systems are independent of integrity computational and data security due to structured data and computational memory. As the size of the cloud data files is increasing in the public and private cloud servers, it is difficult to provide strong data security due to file format and high dimensionality. The computational time and storage space of the conventional attribute-based encryption and decryption models are high during the data integrity verification in the traditional blockchain frameworks. This paper implements a hybrid variable size data integrity algorithm on the heterogeneous cloud supply chain data files for the strong data encryption and decryption process. This work implements an optimized blockchain framework using the advanced heterogeneous integrity computation approach and integrity policy-based attribute encryption and decryption approach for better cloud data security. Experimental results proved that the proposed integrity-based encryption model has better efficiency than the traditional integrity-based encryption frameworks on cloud heterogeneous data types.

Kombinasi Algoritma Kriptografi Vigenere Cipher dan SHA256 untuk Keamanan Basis Data

An organization must consider and manage the security of data storage in databases or databases, and special procedures are needed to protect data from various security risks. The problem in this study is that the population data contained in the Girisuko village administrative service information system has not been encrypted or secured. This can pose a risk that the data stored in the database can be intercepted and misused. In this study, the cryptographic technique used was a combination of the Vigenere Cipher and SHA 256 algorithms to secure or encrypt databases, especially population data in the Girisuko village administrative service information system. The text in the database is encrypted using the Vigenere Cipher, and SHA-256 is used to generate a hash value or a random value that is different from the text in the database. Messages will be encrypted using the Vigenere Cipher and then hashed with SHA-256 simultaneously. As a result, it will be difficult for an attacker to decrypt the text stored in the database because they have to break the Vigenere Cipher encryption, and also have to solve the hash value generated using SHA-256. This combination aims to increase security and maintain the confidentiality of messages from attackers. The application of the Vigenere Cipher and SHA to the village administration service information system application with a real-time database works well, as evidenced by the fast running-time of 0.39 seconds the data encryption process uses the Vigenere Cipher with 894,968 keys/second and an analyzed key length of 7 characters then text on population database successfully secured. By conducting this research, it is hoped that it can contribute to improving database system security.

Protection of personal data in health using symmetric encryption: a comparative study between different algorithms

The LGPD (Lei Geral de Proteção de Dados) aims to protect the right to privacy of personal data of Brazilians. A challenging impasse for several institutions, mainly in the health area, is the process of evolving their systems to the new requirements imposed by the LGPD. The imposition of items such as data encryption and its impact on the performance of these systems brings a discussion about how this additional protection should be provided. This article analyzes several symmetric encryption algorithms available in the PyCryptodome library, such as DES, 3DES, Blowfish, CAST-128 and RC2 to identify which of these would be most suitable for the type of attributes most commonly used in these environments. For the experiments, an application was developed in Python 3 that generates volumes of predefined data, compatible with data from personal attribute management systems in the health area. This data is also applied to the encryption algorithms, where time measurements and function calls are performed during the data encryption and decryption process. The results show the disparity in performance between the different encryption algorithms, as well as the analyzes using different data volumes.