In edge computing environments, app vendors improve user access by caching data across geographically distributed edge servers. However, this architecture remains vulnerable to intentional attacks and accidental failures. Thus, distributed data must be jointly inspected, corruption identified, and repaired efficiently. Addressing these challenges requires a method that efficiently manages vendor resources and minimizes cost. To meet these needs, we propose${\text{O}^{2}\text{DI}}$, an innovative tag-based verifiable outsourcing mechanism with the following capabilities: (i) it enables app vendors to verify cached data on edge servers without accessing the original data, significantly reducing I/O and storage overhead; (ii) it introduces a cutting-edge online/offline technique that improves computational efficiency for both edge servers and app vendors; (iii) it implements a novel batch verification process, enabling rapid and simultaneous verification of multiple files across edge servers; and (iv) it ensures efficient localization and repair of corrupted data. Our comprehensive analysis of${\text{O}^{2}\text{DI}}$demonstrates its robust security within the random oracle model, along with significant improvements in speed and cost-effectiveness over existing methods. Moreover, to demonstrate the practical use of${\text{O}^{2}\text{DI}}$in a real-world system, we present a testbed experiment implemented as a publicly accessible web application that effectively showcases the capabilities of${\text{O}^{2}\text{DI}}$.

The integration of edge computing in the Internet of Medical Things (IoMT) offers great potential for decentralized healthcare services but introduces challenges due to the limited computational capabilities of IoMT devices. Ensuring data security and performance is critical, especially when sensitive medical data pass through untrusted edge devices. Traditional cryptographic methods, such as encryption and signing, are impractical for resource-constrained sensors, particularly when securing data for multiple recipients in an anonymous manner. In this paper, we propose an efficient online/offline broadcast remote signcryption scheme to address these challenges. Our scheme enables medical sensors to securely signcrypt data for multiple recipients, ensuring both confidentiality and integrity. It further guarantees that the ciphertext does not disclose the identities of the recipients, thereby preserving their anonymity. It minimizes online computation by offloading resource-intensive tasks to offline processes. This approach enables remote verification without accessing the original data. Implemented within an edge computing framework, the scheme reduces delays in accessing user data while maintaining robust security guarantees. The security of our solution is rigorously proven under the Bilinear Diffie-Hellman assumption, and real-world implementation demonstrates that the scheme is highly efficient, making it well-suited for practical IoMT applications in healthcare.

In communication systems, ensuring both data integrity and confidentiality is crucial. Traditional methods, such as encryption and signature schemes, handle these aspects separately, leading to inefficiencies. Signcryption techniques, which address both requirements simultaneously, present a more efficient alternative. Nonetheless, they are unsuitable for cloud storage systems due to their reliance on original files for data auditing. Remote data integrity checking (RDIC) methods resolve this issue but compromise data confidentiality. To bridge the gap between signcryption and RDIC approaches, remote signcryption (RSC) has been proposed. However, existing RSC methods lack support for public auditing, rendering data auditing non-outsourcable. This paper introduces publicly verifiable remote signcryption (PVRSC) to address this shortcoming and presents the first concrete PVRSC scheme with public verifiability. We define the security model for PVRSC and prove its robustness based on the hardness of the Bilinear Diffie-Hellman (BDH) problem. Our implementation on real data shows that PVRSC significantly outperforms existing methods, achieving speeds up to 100 times faster and reducing communication costs by half compared to RDIC methods. For outsourced data up to 5MB, PVRSC maintains a communication cost below 8KB during data recovery, a substantial improvement over classical signcryption approaches, which exceed 5MB.

Edge storage presents a viable data storage alternative for application vendors (AVs), offering benefits such as reduced bandwidth overhead and latency compared to cloud storage. However, data cached in edge computing systems is susceptible to intentional or accidental disturbances. This paper proposes a decentralized integrity auditing scheme to safeguard data integrity and counter the traditional reliance on centralized third-party auditors (TPA), which are unfit for distributed systems. Our novel approach employs edge servers (ES) as mutual auditors, eliminating the need for a centralized entity. This decentralization minimizes potential collusion with malicious auditors and biases in audit outcomes. Using a strategic game model, we demonstrate that ESs are more motivated to audit each other than TPAs. The auditing process is addressed as a Nash Equilibrium problem, assuring accurate integrity proof through incentives for ESs. Our scheme's security and performance are rigorously assessed, showing it is secure within the random oracle model, offers improved speed, and is cost-effective compared to existing methods. It also significantly reduces computational and communication overhead.

Edge storage is becoming an increasingly appealing alternative for data owners (DOs), offering benefits like decreased latency and minimized bandwidth usage compared to traditional cloud storage solutions. Nonetheless, stored data within edge servers (ESs) remains vulnerable to disruptions. Existing data integrity auditing schemes face challenges such as the costs of third-party auditors (TPA), unreliable and delayed audit results, and effective management of data inspection concerning time and energy consumption. To tackle these challenges, we introduce DIVO, a decentralized data inspection approach. DIVO leverages ESs as each others’ auditors, removing the necessity for a centralized party, thereby mitigating collision risks and potential biases in audit results. We propose a game-theoretic technique to efficiently manage data inspection and verification offloading to ESs. By formulating the decision-making issue as a strategic game for optimally allocating verification tasks among multiple ESs, we establish the presence of Nash equilibrium and design a strategy to attain it. Through comprehensive security and performance evaluations, DIVO has been shown to operate securely within the random oracle model while delivering notable efficiency improvements over recent methods. Our analysis highlights that DIVO surpasses a wide range of recent approaches in both communication and computation efficiency.

Ensuring data integrity and confidentiality is critical in communication systems. Traditional methods, such as separate encryption and signature schemes, often lead to inefficiencies. While signcryption methods address both needs simultaneously, they are inadequate for data outsourcing systems like cloud computing due to the requirement for original files during data verification. Conversely, remote data integrity checking (RDIC) methods eliminate the need for original files but lack confidentiality. This article fills the gap in cloud security by introducing remote signcryption (RSC) and presenting the first concrete RSC scheme. We demonstrate the application of this novel approach in cloud-assisted Internet of Things (IoT) networks. Our work includes defining the security for an RSC scheme and proving its security under the bilinear Diffie-Hellman (BDH) hardness assumption. Implementing our proposed scheme on real data from trending YouTube video statistics, we found that RSC significantly outperforms existing methods, achieving 100 times faster speed and reducing communication costs by half compared to RDIC methods. Notably, even with 5 MB of outsourced data, RSC keeps the communication cost under 8 kB during data recovery, a substantial improvement over classical signcryption methods that require over 5 MB.

With the widespread growth of cloud computing technology, cloud software services are ubiquitous these days. Using this technology, software providers can sell their products through cloud computing environments in the pay-as-you-use fashion. However, performing secure and accurate calculations in cloud computing environments has become extremely challenging. As the data to be processed by cloud software might be highly sensitive, its confidentiality needs to be taken care of before transferring the data to the cloud server. Also, in addition to the data confidentiality, the security of algorithms employed in the software is of vital importance, and thus software owners may be worried about revealing their algorithms through the cloud server. Homomorphic cryptosystems can provide confidentiality for data to be processed online. However, the confidentiality of algorithms is still an open problem. To address this issue, we put forward a privacy-preserving joint data and function homomorphic encryption (JDF-HE) mechanism. Our JDF-HE can provide confidentiality for both algorithms and data, thereby being suitable for cloud software services. We prove the security of JDF-HE and analyze its performance by evaluating its actual execution overhead. Our performance and security analysis demonstrate that JDF-HE is secure and suitable for real-time applications.

With the rapid development of cloud computing and Internet of Things (IoT), smart health (s-health) is anticipated to enhance healthcare quality significantly. However, data integrity, user anonymity, and authentication concerns have not been adequately addressed in s-health. Remote data integrity checking (RDIC) and digital signature schemes have great potential to address these requirements. Nevertheless, the direct adoption of these schemes suffers from two flaws. Firstly, they incur prohibitively high computation and communication overhead. Secondly, they leak sensitive health information about patients and do not provide complete anonymity. To address these issues, we introduce$\mathbf {A^{3}B}$-$\mathbf {RDV}$, an aggregate anonymous attribute-based remote data verification scheme. In$\mathbf {A^{3}B}$-$\mathbf {RDV}$, the integrity of an arbitrary number of cloud data files can be verified at once without downloading the whole data, thereby saving communication and computation resources. Moreover, in$\mathbf {A^{3}B}$-$\mathbf {RDV}$, data owners can be authenticated by performing highly efficient operations. Also,$\mathbf {A^{3}B}$-$\mathbf {RDV}$provides complete anonymity and supports dishonest-user traceability. We provide security definitions for$\mathbf {A^{3}B}$-$\mathbf {RDV}$and prove its security under the hardness assumption of the bilinear Diffie-Hellman (BDH) problem. Performance comparisons and experimental results indicate that$\mathbf {A^{3}B}$-$\mathbf {RDV}$is more efficient and expressive than state-of-the-art approaches.