Federated learning has recently been applied to recommendation systems to protect user privacy. In federated learning settings, recommendation systems can train recommendation models by collecting the intermediate parameters instead of the real user data, which greatly enhances user privacy. In addition, federated recommendation systems (FedRSs) can cooperate with other data platforms to improve recommendation performance while meeting the regulation and privacy constraints. However, FedRSs face many new challenges such as privacy, security, heterogeneity, and communication costs. While significant research has been conducted in these areas, gaps in the surveying literature still exist. In this article, we: 1) summarize some common privacy mechanisms used in FedRSs and discuss the advantages and limitations of each mechanism; 2) review several novel attacks and defenses against security; 3) summarize some approaches to address heterogeneity and communication costs problems; 4) introduce some realistic applications and public benchmark datasets for FedRSs; and 5) present some prospective research directions in the future. This article can guide researchers and practitioners understand the research progress in these areas.

Improving efficiency and performance is an important topic in the world today. As it is well-known, cooperative computing is an effective and traditional approach, and it is widely used in various fields. Inspired by this idea, take E-commerce for example, Security is one of its important indicators. In E-commerce, the security technology has become a major issue restricting the rapid development and popularization of E-commerce. Existing solutions leverage blockchain protocols to improve the credibility of transactions, but most of them have some limitations, such as a lower throughput and higher consensus latency, and these problems make blockchain technology difficult to be widely used. This paper presents a trusted framework (ETT F) using blockchain protocol in E-commerce to achieve a higher credible trading. ETTF includes a peer blockchain protocol (PBP) based on a peer blockchain architecture to support the storage of massive transactions and instant transactions. In PBP, the throughput scales are nearly linearly increased with the computation: the more computing power available, the more blocks are selected per unit time. Besides, in order to ensure a higher security of transactions we have introduced a strong consensus algorithm(ECA) in E-commerce. ETTF is also efficient because the number of messages it requires is nearly linear in the network size. Compared to Bitcoin-derived blockchain, ETTF shows better performance on throughput, latency, and capacity in E-commerce.

The interpretability of neural networks has garnered significant attention. In the domain of computer vision, gradient-based feature attribution techniques like RectGrad have been proposed to utilize saliency maps to demonstrate feature contributions to predictions. Despite advancements, RectGrad falls short in category discrimination, producing similar saliency maps across categories. This paper pinpoints the ineffectiveness of threshold-based strategies in RectGrad for distinguishing feature gradients and introduces Class activation map Guided BackPropagation (CGBP) to tackle the issue. CGBP leverages class activation maps during backpropagation to enhance gradient selection, achieving consistent improvements across four models (VGG16, VGG19, ResNet50, and ResNet101) on ImageNet’s validation set. Notably, on VGG16, CGBP improves SIC, AIC, and IS scores by 10.3%, 11.5%, and 4.5%, respectively, compared to RectGrad while maintaining competitive DS performance. Moreover, CGBP demonstrates greater sensitivity to model parameter changes than RectGrad, as confirmed by a sanity check. The proposed method has broad applicability in scenarios like model debugging, where it identifies causes of misclassification, and medical image diagnosis, where it enhances user trust by aligning visual explanations with clinical insights.