Homomorphic Encryption Research Articles

Homomorphic Encryption for Secure Ad Targeting: Balancing Privacy and Personalization in Digital Advertising

This article explores the application of homomorphic encryption (HE) in secure ad targeting, addressing the critical challenge of balancing personalized advertising with user privacy concerns in the digital advertising ecosystem. We examine the fundamentals of HE, its integration into ad targeting processes, and propose a privacy-preserving ad platform architecture. Through a comprehensive feasibility analysis and performance evaluation, we assess the technical challenges, computational overhead, and scalability issues associated with implementing HE in real-time ad serving. Our findings indicate that while HE offers strong privacy guarantees, it currently faces limitations in terms of latency and throughput compared to traditional ad targeting methods. We analyze the trade-offs between privacy protection and targeting effectiveness, highlighting the impact on ad relevance and personalization. The article also discusses future directions, including advancements in HE algorithms, integration with other privacy-enhancing technologies, and regulatory considerations. By synthesizing current research and experimental results, this work provides valuable insights into the potential of HE to revolutionize privacy-preserving ad targeting, paving the way for a more secure and privacy-conscious digital advertising future.

Integrating Blockchain and Homomorphic Encryption to Enhance Security and Privacy in Project Management and Combat Counterfeit Goods in Global Supply Chain Operations

The proliferation of counterfeit goods and data privacy concerns in global supply chain operations poses a significant risk to organizations and end-users alike. This paper explores the integration of blockchain technology and homomorphic encryption as dual mechanisms to enhance security and privacy in project management and supply chain operations. Blockchain offers an immutable, decentralized ledger that provides traceability and authenticity across supply chain nodes, while homomorphic encryption enables secure data processing and analysis without compromising sensitive information. The synergy of these technologies presents a robust framework to address counterfeit risks, facilitating end-to-end product authentication and allowing for secure, real-time collaboration in project management settings. This integration minimizes vulnerabilities in data handling and improves compliance with privacy regulations by securing data at rest and in transit. By evaluating case studies and recent advancements, this paper highlights the potential of blockchain and homomorphic encryption to redefine security protocols, fostering a trustworthy and resilient supply chain ecosystem. Future research directions are recommended to expand the practical applications and address scalability challenges associated with these emerging technologies.

Secure Face Recognition Using Fully Homomorphic Encryption and Convolutional Neural Networks

Secure Face Recognition Using Fully Homomorphic Encryption and Convolutional Neural Networks

EADC: An Efficient Anonymous Data Collection Scheme with Blockchain in Internet of Things

The integration of smart contracts (SCs) within blockchain technology represents a pivotal direction in the evolution of the Internet of Things (IoT), enabling decentralization and enhancing user trust in the system. However, ensuring data privacy is a fundamental challenge that must be addressed during the deployment of these SCs. Many scholars have adopted data aggregation to protect privacy, but these methods are difficult to achieve fine-grained data collection. To this end, this paper proposes an efficient anonymous data collection (EADC) scheme suitable for the IoT environment. The scheme combines matrix algorithms with homomorphic encryption (HE) technology to effectively cut off the connection between users and data during data upload. In addition, the EADC scheme introduces a sophisticated data grouping protocol to improve the overall efficiency of the system. Analysis shows that the scheme can achieve efficient data collection without compromising user privacy.

Implementing the Grover algorithm in homomorphic encryption schemes

We apply quantum homomorphic encryption (QHE) schemes suitable for circuits with a polynomial number of T+T† gates to Grover's algorithm, performing a simulation in Qiskit of a Grover circuit that contains three qubits. The T+T†-gate complexity of Grover's algorithm is also analyzed in order to show that any Grover circuit can be evaluated homomorphically in an efficient manner. We discuss how to apply these QHE schemes to allow for the efficient homomorphic evaluation of any Grover circuit composed of n qubits using n−2 extra ancilla qubits. We also show how the homomorphic evaluation of the special case where there is only one marked item can be implemented using an algorithm that makes the decryption process more efficient compared with the standard Grover algorithm. Published by the American Physical Society 2024

Privacy-Preserving Techniques in Generative AI and Large Language Models: A Narrative Review

Generative AI, including large language models (LLMs), has transformed the paradigm of data generation and creative content, but this progress raises critical privacy concerns, especially when models are trained on sensitive data. This review provides a comprehensive overview of privacy-preserving techniques aimed at safeguarding data privacy in generative AI, such as differential privacy (DP), federated learning (FL), homomorphic encryption (HE), and secure multi-party computation (SMPC). These techniques mitigate risks like model inversion, data leakage, and membership inference attacks, which are particularly relevant to LLMs. Additionally, the review explores emerging solutions, including privacy-enhancing technologies and post-quantum cryptography, as future directions for enhancing privacy in generative AI systems. Recognizing that achieving absolute privacy is mathematically impossible, the review emphasizes the necessity of aligning technical safeguards with legal and regulatory frameworks to ensure compliance with data protection laws. By discussing the ethical and legal implications of privacy risks in generative AI, the review underscores the need for a balanced approach that considers performance, scalability, and privacy preservation. The findings highlight the need for ongoing research and innovation to develop privacy-preserving techniques that keep pace with the scaling of generative AI, especially in large language models, while adhering to regulatory and ethical standards.

HMC-FHE: A Heterogeneous Near Data Processing Framework for Homomorphic Encryption

HMC-FHE: A Heterogeneous Near Data Processing Framework for Homomorphic Encryption

DSDOS Cloud: A Decentralized Secure Data Outsourcing System With Hybrid Encryption, Blockchain Smart Contract‐Based Access Control, and Hash Authentication Codes for Cloud Security

ABSTRACTWith the increasing trend of outsourcing data to cloud services, ensuring data security and privacy has become crucial. Typically, data are stored on cloud servers in encrypted form to mitigate risks. However, accessing the encrypted data requires an access key distributed by a third party. If this third party is untrustworthy, it poses a significant security threat to the system. To address this challenge, we propose a Decentralized Secure Data Outsourcing System (DSDOS) that uses blockchain technology to ensure data security and privacy. The DSDOS system comprises three modules: data security and privacy, access control and authorization, and data integrity and availability. The data security and privacy module uses a hybrid encryption scheme that combines Advanced Encryption Standard (AES), partially homomorphic encryption (PHE), and Diffie–Hellman (DH) to ensure secure data storage and access. The access control and authorization module uses a blockchain‐based smart contract system to manage access to the encrypted data. The data integrity and availability module uses hash‐based message authentication code (HMAC) to ensure that the data are not tampered with and is always available. We conducted a security and performance analysis of the DSDOS system and found that it outperforms previous schemes in terms of security and performance. The DSDOS system is a secure and privacy‐preserving data outsourcing system that can be used to mitigate the security risks associated with traditional cloud storage systems.

Privacy preserving verifiable federated learning scheme using blockchain and homomorphic encryption

This paper introduces a novel Privacy-Preserving Verifiable Federated Learning (PPVFL) scheme that integrates blockchain technology and homomorphic encryption to address critical challenges in decentralized machine learning. The proposed scheme ensures data privacy, integrity, verifiability, robust security, and efficiency in collaborative learning environments, particularly in sensitive domains such as healthcare. By leveraging blockchain’s decentralized, immutable ledger and homomorphic encryption’s capability to perform computations on encrypted data, the model maintains the confidentiality of sensitive information throughout the learning process. The inclusion of Byzantine fault tolerance and Elliptic Curve Digital Signature Algorithm (ECDSA) further enhances the system’s security against malicious attacks and data tampering, while the optimization of computational processes ensures efficient model training and communication. The novelty of this work lies in the seamless integration of blockchain and homomorphic encryption within a federated learning framework, specifically tailored for post-quantum cryptography, a combination that has not been extensively explored in prior research. This research represents a significant advancement in secure and efficient federated learning, offering a promising solution for industries that prioritize data privacy, security, and trust in collaborative machine learning. The effectiveness, security, and efficiency of the PPVFL scheme were validated using the Glaucoma dataset. The proposed method outperformed baseline federated learning algorithms, achieving a Dice coefficient of 0.918 and a Hausdorff distance of 4.05 on Severe Glaucoma (SG) cases, compared to 0.905 and 5.27, respectively, with traditional FedAvg. Moreover, the integration of blockchain and homomorphic encryption ensured that data privacy was upheld without compromising model performance, while efficient computation and communication processes minimized latency and resource consumption. This study contributes a robust, privacy-preserving, secure, efficient, and verifiable federated learning framework that addresses the pressing need for secure and scalable data management in distributed machine learning environments.

Leveraging blockchain for sustainable supply chain management: A data privacy and security perspective

This review examines how blockchain technology can be leveraged to enhance data privacy and security in sustainable supply chain management (SSCM). As global supply chains become increasingly complex and the demand for sustainability grows, ensuring data privacy and security has become a critical concern. Traditional supply chain systems often face challenges such as data breaches, lack of transparency, and difficulty in tracing products and materials. Blockchain technology, with its decentralized, immutable, and transparent architecture, offers a promising solution to these challenges. Blockchain can enhance data security by ensuring that data is tamper-proof, traceable, and encrypted, thus protecting sensitive information across the supply chain. It provides transparency while allowing permissioned access, ensuring that stakeholders can verify data without exposing confidential information. Furthermore, privacy-preserving technologies such as zero-knowledge proofs and homomorphic encryption allow verification of data without compromising its security. Smart contracts enable automated compliance with regulatory frameworks like GDPR, reducing the risk of human error and improving operational efficiency. The integration of blockchain in SSCM can improve traceability, transparency, and accountability, thereby promoting environmental and social sustainability. By tracking the origin and journey of goods, blockchain helps verify ethical sourcing practices and reduce carbon footprints. However, the technology also presents challenges, including scalability, integration with legacy systems, and cost considerations. Through case studies in industries such as food, textiles, and renewable energy, this review highlights the practical applications and benefits of blockchain for SSCM. It concludes that blockchain has the potential to revolutionize supply chain operations, but careful consideration must be given to overcoming its technical and financial barriers to widespread adoption.

ENERGY EFFICIENT ROUTING PROTOCOL FOR SECURITY ANALYSIS SCHEME USING HOMOMORPHIC ENCRYPTION

Wireless Sensor Networks (WSNs) have gained widespread interest as a result of developments in IT technology and the electronics industry. This ground-breaking sensing technology consists of multiple sensor nodes or motes that are placed in an atmosphere to detect constantly changing physical phenomena. These compact sensor nodes gather and interpret data via radio waves. The tiny size of these sensors is advantageous since they may be readily incorporated into any system or system. This capability has prompted the adoption of WSNs, particularly for form monitoring and tracking; most notably, monitoring apps. However, this small scale of sensor nodes limits the capacity of resources. Usually, the WSNs are installed in environments of unsafe or difficult human interference. Critical decisions in emergency applications can require sensible knowledge. It is necessary to check the network security. To extend the network security using Homomorphic Encryption effectively, the available resources must be expanded to a full view. This refers to the development of energy-efficient routing protocol strategies to ensure low energy consumption of common routing protocols and improve the availability and security of WSNs. Homomorphic encryption is effective in improving the security of wireless sensor networks.

A Privacy-Preserving Scheme for a Traffic Accident Risk Level Prediction System

Due to the expansion of Artificial Intelligence (AI), especially Machine Learning (ML), it is more common to face confidentiality regulations about using sensitive data in learning models generally hosted in cloud environments. Confidentiality regulations such as HIPAA and GDPR seek to guarantee the confidentiality and privacy of personal information. Input and output data of a learning model may include sensitive data that must be protected. Adversaries could intercept and exploit this data to infer more sensitive data or even to determine the structure of the prediction model. To guarantee data privacy, one option could be encrypting data and making inferences over encrypted data. This strategy would be challenging for learning models that now must receive encrypted data, make inferences over encrypted data, and deliver encrypted data. To address this issue, this paper presents a privacy-preserving machine learning approach using Fully Homomorphic Encryption (FHE) for a model that predicts risk levels of suffering a traffic accident. Despite the limitations of experimenting with FHE on machine learning models using a low-performance computer, limitations that are undoubtedly overcome by using high-performance computational infrastructure, we built some encrypted models. Among the encrypted models based on Decision Trees, Random Forests, XGBoost, and Fully Connected Neural Networks (FCNN), the model based on FCNN reached the highest accuracy (80.1%) for the lowest inference time (8.476 s).

Design of intelligent algorithm for object search based on IoT digital images

With the development of artificial intelligence, traditional object search and image recognition have been replaced by the Internet of Things and artificial intelligence. However, traditional object search algorithms often lack accuracy and low precision. Therefore, this study proposes a new intelligent encryption algorithm to address the issues of insufficient accuracy in object search algorithms and image recognition algorithms. The new algorithm ensures the security of user data and the response efficiency of the model during the conversation process by integrating fully homomorphic encryption technology and dynamic sparse attention mechanism. The dynamic sparse attention mechanism introduced simultaneously improves the model's ability to handle long sequence data by dynamically adjusting attention weights. Experimental results showed that the precision of the proposed algorithm was 0.05 % higher than that of random algorithms and 0.19 % higher than that of sorting algorithms. The recall rate of the proposed algorithm was 0.14 % higher than that of random algorithms and 0.16 % higher than that of sorting algorithms. The research algorithm can identify objects with certain characteristics and is suitable for specific environments, greatly reducing the probability of data leakage in object search and providing new ideas for research in this field.

Overview of homomorphic encryption technology for data privacy

This study examines the overview of homomorphic encryption technology for data privacy. In the era of big data, the growing need to utilize vast amounts of information while ensuring privacy and security has become a significant challenge. Homomorphic encryption technology has gained attention as a solution for privacy-preserving data processing, allowing computations on encrypted data without exposing sensitive information. This study introduces the concept of data privacy preservation and explores the evaluation of homomorphic encrypted technology. The focus is on analyzing both partial and full homomorphic encryption methods, highlighting their respective characteristics, evaluation criteria, and the current state of research. Partial homomorphic encryption supports limited operations, while full homomorphic encryption enables unlimited computation on encrypted data, though both face challenges related to computational overhead and efficiency. Additionally, this paper addresses the ongoing issues and limitations associated with homomorphic encryption, such as its complexity, large encryption volumes, and difficulties in handling large-scale datasets. Despite these challenges, researchers continue to refine the technology and expand its applications in cloud computing, big data analytics, and privacy-preserving computing environments. This study also discussed potential future research avenues aimed at improving the scalability, efficiency, and security of homomorphic encryption to support broader, real-world applications. Ultimately, homomorphic encryption is positioned as a key enabler for secure data utilization in an increasingly privacy-conscious digital landscape.

Integrating Homomorphic Encryption in IoT Healthcare Blockchain Systems

Integrating Homomorphic Encryption in IoT Healthcare Blockchain Systems

Federated split learning via dynamic aggregation and homomorphic encryption on non-IID data

Federated split learning via dynamic aggregation and homomorphic encryption on non-IID data

Research on Blockchain Interactive Zero Knowledge Proof Privacy Protection Scheme Based on Improved Paillier Homomorphic Encryption

In the context of the digital age, data privacy and security issues are increasingly prominent. Blockchain technology plays an important role in data sharing due to its transparency and immutability, but it also brings the risk of privacy leakage. Zero knowledge proof technology provides a solution for verifying data correctness without exposing data content, which is particularly important for blockchain as it can ensure the validity and compliance of transactions while protecting user privacy. Although zero knowledge proof is quite mature in theory, its application in blockchain systems still faces challenges such as computational efficiency, complexity of smart contracts, and system compatibility. This study aims to propose a privacy protection scheme that supports interactive zero knowledge proof by improving the homomorphic encryption Paillier algorithm, in order to enhance the privacy protection capability of blockchain systems and maintain system efficiency and security. The study will adopt an interdisciplinary approach, combining cryptography, computer science, and network security theory, to deeply analyze the application effect of zero knowledge proof technology in blockchain, explore its optimization space and applicability.

Augmenting Data Privacy Protocols and Enacting Regulatory Frameworks for Cryptocurrencies via Advanced Blockchain Methodologies and Artificial Intelligence

This study examines the effectiveness of current data privacy protocols within cryptocurrency platforms, focusing on encryption strength, anonymity techniques, and AI-powered regulatory compliance tools. Data were sourced from CoinMarketCap and Kaggle, including metrics like Bit Strength, Breach Incidents, and Anonymity Scores, which were analyzed using descriptive statistics, t-tests, and logistic regression. Results showed no significant relationship between encryption strength and breach incidents (p = 0.817), indicating that encryption strength may not be a primary factor in breach prevention. The weak correlation between encryption strength and breaches suggests that other elements, such as platform vulnerabilities or user behaviour, could play a more critical role in security. AI systems, evaluated through metrics like precision (0.168), recall (0.204), and F1 score (0.184), struggled with false positives, showing limitations in accurately detecting breaches and highlighting the need for more refined AI models. Advanced blockchain technologies like Zero-Knowledge Proofs and Homomorphic Encryption enhanced privacy but increased computational costs. It is recommended that hybrid encryption methods be adopted to balance privacy and performance and improve AI systems for more accurate breach detection. Governments must create clear regulations that encourage innovation while ensuring compliance.

Privacy‐Preserving Optimization Algorithm for Distributed Energy Management Over Time‐Varying Graphs: A State Decomposition Method

ABSTRACTThe rapid advancements of intelligent technologies have brought about the potential vulnerability of confidential gradient information linked to cost functions when solving distributed optimization and its related problems. Within the context of distributed energy management, safeguarding such private information has risen to paramount importance. This article investigates a distributed energy management problem (DEMP) to minimize cost while simultaneously satisfying multiple local constraints and protecting the private gradient information of the cost function. To this end, a new privacy‐preserving distributed optimization algorithm under the framework of gradient tracking over time‐varying graphs is proposed for solving the DEMP. Specifically, the auxiliary variables are designed for each node in the algorithm to update the gradient while the original state variables are responsible for the interaction with original neighbors and auxiliary variables. Consequently, the devised algorithm can protect the confidentiality of private cost gradient information, even in the presence of eavesdroppers within the network. In contrast to the homomorphic encryption, signal masking method, and some other algorithms without utilizing the state decomposition, the designed algorithm does not require extra information or computing resources. Moreover, it is proven that the designed algorithm could theoretically converge to the exact optimum of the DEMP at a rate of under some mild assumptions.

FedNIC: enhancing privacy-preserving federated learning via homomorphic encryption offload on SmartNIC

Federated learning (FL) has emerged as a promising paradigm for secure distributed machine learning model training across multiple clients or devices, enabling model training without having to share data across the clients. However, recent studies revealed that FL could be vulnerable to data leakage and reconstruction attacks even if the data itself are never shared with another client. Thus, to resolve such vulnerability and improve the privacy of all clients, a class of techniques, called privacy-preserving FL, incorporates encryption techniques, such as homomorphic encryption (HE), to encrypt and fully protect model information from being exposed to other parties. A downside to this approach is that encryption schemes like HE are very compute-intensive, often causing inefficient and excessive use of client CPU resources that can be used for other uses. To alleviate this issue, this study introduces a novel approach by leveraging smart network interface cards (SmartNICs) to offload compute-intensive HE operations of privacy-preserving FL. By employing SmartNICs as hardware accelerators, we enable efficient computation of HE while saving CPU cycles and other server resources for more critical tasks. In addition, by offloading encryption from the host to another device, the details of encryption remain secure even if the host is compromised, ultimately improving the security of the entire FL system. Given such benefits, this paper presents an FL system named FedNIC that implements the above approach, with an in-depth description of the architecture, implementation, and performance evaluations. Our experimental results demonstrate a more secure FL system with no loss in model accuracy and up to 25% in reduced host CPU cycle, but with a roughly 46% increase in total training time, showing the feasibility and tradeoffs of utilizing SmartNICs as an encryption offload device in federated learning scenarios. Finally, we illustrate promising future study and potential optimizations for a more secure and privacy-preserving federated learning system.