Federated Class-Incremental Learning (FCIL) enables distributed models to continuously learn new categories while preserving privacy, which suffers from the problem of catastrophic forgetting. To address this issue, generative replay has emerged as a mainstream solution, yet its performance is hampered by two fundamental bottlenecks: (1) low-fidelity synthesis, where generated visual samples fail to effectively represent historical knowledge, and (2) class imbalance in FCIL, which undermines fair learning across classes. In this paper, we propose a novel generative replay framework called FedART (Federated Adaptive Replay with Text-anchors). To combat low-fidelity synthesis, FedART employs a text-anchored initialization strategy. Instead of optimizing from a random start, this approach provides strong semantic priors to guide the generation process. To tackle class imbalance, we design a dual adaptive aggregation mechanism. This mechanism applies tailored weighting strategies at both the generator and classifier levels, leveraging local training dynamics to ensure both the quality of generative knowledge and the fairness of classifier aggregation. Extensive experiments on CIFAR-100 and Tiny-ImageNet demonstrate that FedART significantly outperforms state-of-the-art methods, achieving an accuracy of up to 43.62% and establishing a new and robust benchmark for enhancing the effectiveness of generative replay in FCIL.

Multimodal deep learning technologies have advanced significantly, which brings extensive applications in diverse fields. The substantial computational demands of training and prediction in multimodal deep learning have made the End-Edge-Cloud (EEC) framework popular. It is essential to protect multimodal data and model privacy in such a framework. However, traditional cryptographic methods, though secure for data and models at edge nodes, cause efficiency limitations. In this paper, we propose SecMdp, an SGX-assisted secure computational framework for multimodal data in the EEC architecture. Edge nodes are equipped with the trusted execution environment (e.g., Intel SGX) to run multimodal algorithms. Additionally, to address the side-channel attacks of SGX, we present an enhanced PathORAM algorithm, MM_PathORAM, for the multimodal training and prediction processes, which are tailored for multimodal deep learning scenarios. It accelerates multimodal data access while protecting data privacy and model security. Experimental evaluation supports the effectiveness of our design in preserving edge computing efficiency. It demonstrates negligible impact on the speed of multimodal data loading, the configuration of model parameters during training, or the accuracy of predictions.

Federated learning has emerged as a promising paradigm for large-scale collaborative training tasks, harnessing diverse local datasets from different clients to jointly train global models. In real-world implementations, client data could have label noise, causing the quality of the global model to be influenced. Existing label-correction solutions assume all the clients are discreet and fail to consider detecting the malicious clients, thus are not practical or privacy-preserving. In this paper, we present zkCor, an efficient and reliable label noise correction scheme with zero-knowledge confidentiality. Our method is designed upon FedCorr [1], but with more relaxed security assumptions. zkCor is established from the ingenious synergy of the label noise correction protocol and the zero-knowledge proof (ZKP), requiring each client to provide a computation integrity proof to the aggregator in each iteration. Thus, clients are forced to jointly guarantee label-correction reliability. We further devise a batch ZKP that is efficient and more suitable for federated learning settings. We rigorously illustrate the building blocks of zkCor and complete the prototype implementation. The extensive experiments demonstrate that zkCor can gain at least 2 to 30 times better performance than the baseline approach on verification workloads with nearly no extra proof time cost from clients.

Quality control in crowdsourcing is challenging due to the heterogeneous nature of the workers. The state-of-the-art solutions attempt to address the issue from the technical perspective, which may be costly because they function as an additional procedure in crowdsourcing. In this paper, an economics based idea is adopted to embed quality control into the crowdsourcing process, where the requestor can take advantage of the market power to stimulate the workers for submitting high-quality jobs. Specifically, we employ two sequential games to model the interactions between the requestor and the workers, with one considering binary strategies while the other taking continuous strategies. Accordingly, two incentive algorithms for improving the job quality are proposed to tackle the sequential crowdsourcing dilemma problem. Both algorithms are based on a sequential zero-determinant (ZD) strategy modified from the classical ZD strategy. Such a revision not only provides a theoretical basis for designing our incentive algorithms, but also enlarges the application space of the classical ZD strategy itself. Our incentive algorithms have the following desired features: 1) they do not depend on any specific crowdsourcing scenario; 2) they leverage economics theory to train the workers to behave nicely for better job quality instead of filtering out the unprofessional workers; 3) no extra costs are incurred in a long run of crowdsourcing; and 4) fairness is realized as even the requestor (the ZD player), who dominates the game, cannot increase her utility by arbitrarily penalizing any innocent worker.

In recent years, smart sports equipment and body sensor systems have become popular in professional and amateur sports. One of a few remaining problems in real-time applications is the discovery of knowledge from the embedded sensors data. In sports training, such knowledge helps accelerated motor learning. The authors start with exploring the possibilities of the classification of golf swing performance with the 1-D convolutional neural network (CNN) in real-time. They thoroughly investigate multiple golf swing data classifiers based on CNNs fed with multi-sensor signals. The authors test the possibilities of real-time performance of CNN methods on the multi-length sequences. In addition, they thoroughly evaluate the performance of their well-trained CNN-based classifier on the aforementioned test set in terms of common indicators. Experiments and corresponding results show that the authors' models can satisfy the real-time requirement of the accuracy of the classification and outperform support vector machine (SVM).