Recommendation systems powered by artificial intelligence (AI) are widely used to improve user experience. However, AI inevitably raises privacy leakage and other security issues due to the utilization of extensive user data. Addressing these challenges can protect users' personal information, benefit service providers, and foster service ecosystems. Presently, numerous techniques based on differential privacy have been proposed to solve this problem. However, existing solutions encounter issues such as inadequate data utilization and a tenuous trade-off between privacy protection and recommendation effectiveness. To enhance recommendation accuracy and protect users' private data, we propose ID-SR, a novel privacy-preserving social recommendation scheme for trustworthy AI based on the infinite divisibility of Laplace distribution. We first introduce a novel recommendation method adopted in ID-SR, which is established based on matrix factorization with a newly designed social regularization term for improving recommendation effectiveness. We then propose a differential privacy-preserving scheme tailored to the above method that leverages the Laplace distribution's characteristics to safeguard user data. Theoretical analysis and experimentation evaluation on two publicly available datasets demonstrate that our scheme achieves a superior balance between privacy protection and recommendation effectiveness, ultimately delivering an enhanced user experience.

—With the increasing rates of interconnected Internet of Things (IoT) devices within software-defined networking (SDN) environments, Distributed Denial-of-Service (DDoS) attacks have become increasingly common. As a result of this challenge, novel detection and classification methods must be developed based on the unique characteristics of SDN-supported IoT networks. This article proposes a novel approach to detecting and categorizing DDoS attacks that have been optimized specifically for such environments. As part of our methodology, we integrate convolutional neural networks (CNNs) and long-short-term memory (LSTM) models into a multilevel deep neural network architecture. With this hybrid architecture, complex spatial and temporal patterns can be automatically extracted from raw network traffic data to facilitate comprehensive analysis and accurate identification of DDoS attacks. We validate the efficacy and superiority of our proposed approach over traditional machine learning algorithms by conducting rigorous experiments on real-world data sets. Our findings underscore the potential of the multilevel deep neural network approach as a robust and scalable solution for mitigating DDoS attacks in SDN-supported IoT networks. By improving network security and resilience to evolving threats, our methodology contributes to safeguarding critical infrastructures in the era of interconnected IoT ecosystems.

Updatable encryption (UE) enables the cloud server to update the previously sourced encrypted data to a new key with only an update token received from the client. Two interesting works have been proposed to clarify the relationships among various UE security notions. Jiang (ASIACRYPT 2020) proved the equivalence of every security notion in the bi-directional and uni-directional key update settings and further, the security notion in the no-directional key update setting is strictly stronger than the above two. In contrast, Nishimaki (PKC 2022) proposed a new definition of uni-directional key update that is called the backward-leak uni-directional key update, and showed the equivalence relation by Jiang does not hold in this setting. We present a detailed comparison of every security notion in the four key update settings and prove that the security in the backward-leak uni-directional key update setting is actually equivalent to that in the no-directional key update setting. Our result reduces the hard problem of constructing no-directional key update UE schemes to the construction of those with backward-leak uni-directional key updates.

Wireless body area networks (WBAN) enable ubiquitous monitoring of patients, which can change the future of healthcare services overwhelmingly. As the collected data of patients usually contain sensitive information, how to collect, transfer, store and share data securely and properly has become a concerning issue. Attribute-based encryption (ABE) can achieve data confidentiality and fine-grained access control simultaneously. Identity-based ring signature (IBRS) allows patients to prove their identity without leaking any extra (private) information. However, the heavy computational burden of ABE and IBRS is intolerable for most power-limited mobile devices, which account for a large proportion of WBAN devices. This paper combines the attribute-based online/offline encryption (ABOOE) and IBRS to achieve an outsourced online/offline hybrid signcryption ( O3 HSC) scheme. As far as we know, this scheme is the first signcryption scheme that adopts IBRS and satisfies online/offline signcryption simultaneously. O3 HSC divides the key generation and signcryption into offline and online phases to increase the throughput of the central authority and save the power resources of mobile devices, respectively. Besides, outsourced decryption and public signature verification are also realized. O3 HSC achieves security under CCA and CMIA, and the performance analysis shows that O3 HSC is a lightweight and applicable scheme for WBAN.