With the improvement of the quality and resolution of remote sensing (RS) images, scene recognition tasks have played an important role in the RS community. However, due to the special bird’s eye view image acquisition mode of imaging sensors, it is still challenging to construct a discriminate representation of diverse and complex scenes to improve RS image recognition performance. Capsule networks that can learn the spatial relationship between the features in an image has a good image classification performance. However, the original capsule network is not suitable for images with a complex background. To address the above issues, this paper proposes a novel end-to-end capsule network termed DS-CapsNet, in which a new multi-scale feature enhancement module and a new Caps-SoftPool method are advanced by aggregating the advantageous attributes of the residual convolution architecture, Diverse Branch Block (DBB), Squeeze and Excitation (SE) block, and the Caps-SoftPool method. By using the residual DBB, multiscale features can be extracted and fused to recover a semantic strong feature representation. By adopting SE, the informative features are emphasized, and the less salient features are weakened. The new Caps-SoftPool method can reduce the number of parameters that are needed in order to prevent an over-fitting problem. The novel DS-CapsNet achieves a competitive and promising performance for RS image recognition by using high-quality and robust capsule representation. The extensive experiments on two challenging datasets, AID and NWPU-RESISC45, demonstrate the robustness and superiority of the proposed DS-CapsNet in scene recognition tasks.

A Radio Frequency Identification (RFID) grouping-proof protocol is to generate an evidence of the simultaneous existence of a group of tags and it has been applied to many different fields. For current grouping-proof protocols, there still exist some flaws such as low grouping-proof efficiency, being vulnerable to trace attack and information leakage. To improve the secure performance and efficiency, we propose a lightweight RFID grouping-proof protocol based on parallel mode and DHCP (Dynamic Host Configuration Protocol) mechanism. Our protocol involves multiple readers and multiple tag groups. During the grouping-proof period, one reader and one tag group are chosen by the verifier by means of DHCP mechanism. When only a part of the tags of the chosen group exist, the protocol can also give the evidence of their co-existence. Our protocol utilizes parallel communication mode between reader and tags so as to ensure its grouping-proof efficiency. It only uses Hash function to complete the mutual authentication among verifier, readers and tags. It can preserve the privacy of the RFID system and resist the attacks such as eavesdropping, replay, trace and impersonation. Therefore the protocol is secure, flexible and efficient. It only uses some lightweight operations such as Hash function and a pseudorandom number generator. Therefore it is very suitable to some low-cost RFID systems.

Federated learning, unlike centralized training, enables multiple clients to train a global model without exposing raw data, making it useful for applications such as medical diagnosis in smart healthcare and mobile edge networks. This setting is vulnerable to dynamic collusive attacks, where colluding clients coordinate abnormal parameter updates and adjust their strategies across training rounds. Existing studies address this problem with isolated mechanisms that focus on a single defense stage, but such mechanisms are insufficient for attacks that evolve across rounds. To address this challenge, we propose reputation-aware Stackelberg incentive aggregation (RSIA) to mitigate the influence of dynamic collusive attacks while balancing model utility in federated learning. Specifically, we first use incentive rules before local training to make repeated collusive behavior less beneficial. We then update client reputation after each round, so earlier unreliable behavior affects later incentives. Finally, we use reputation and update reliability to weight client updates, reducing the influence of abnormal updates on global model training. Experiments on three datasets show that RSIA reduces the average effective attack success rate by 84.9% compared with representative state-of-the-art (SOTA) methods. RSIA also maintains competitive test accuracy, providing a favorable trade-off between model utility and attack suppression.