Robust object detection under varying weather conditions (e.g., rain, fog, and snow) presents significant challenges for industrial vision systems due to inherent visual degradations in manufacturing sites and outdoor facilities. While knowledge distillation offers promising potential by feature imitating and logit mimicking, existing methods face two critical limitations: first, inadequate mechanisms for effectively transferring localization capabilities in the presence of severe image degradation, and second, suboptimal strategies for identifying optimal distillation regions. To address these issues, we present a symmetric localization distillation loss based on the Jensen–Shannon divergence. Its mathematical characteristics, e.g., boundedness, symmetry, and gradient smoothness, enable robust preservation of spatial relationships and stabilize training processes. In addition, we present an adaptive label assignment strategy to select distillation regions, thus reducing the sparsity of positive samples during our knowledge distillation process. This work is the first one to apply knowledge distillation to object detection in inclement weather conditions. Extensive experiments on three challenging datasets show that our method improves the student model's object detection accuracy while maintaining its inference speed.

Although remarkable advances have been achieved in generic object detection, small object detection (SOD) remains challenging owing to small objects’ information loss and noisy representation caused by their non-uniform distribution. Their limited width and height, scale variations, and redundant computation make SOD hard. To overcome them, this work proposes a new SOD method based on sparse convolutional network (SCNet) and Query Mechanism called QuerySOD. First, an extended feature pyramid network is constructed for extracting feature maps of small objects with more regional details. Then, a Sparse Head is neatly designed by using SCNet for accelerating the interfering speed and obtaining weights of each layer. After that, a Query Mechanism is innovatively introduced for harvesting the benefit of sparse value feature maps from the Sparse Head. QuerySOD is evaluated on public benchmarks including COCO and VisDrone. Finally, we apply it on ‘Jinghai’ unmanned survey vehicles and receive excellent SOD performance from this real-world application.

The 5G technology will promote the development of vehicle ad hoc networks (VANET). However, almost all the existing authentication protocols rely on a completely trusted authority (TA), which undoubtedly raises a heavy burden on the TA. On the other hand, these protocols can rarely resist some special attacks, such as registration authority leaks registration information attack and ephemeral secret leakage attack. To address these problems, based on the self‐certified public keys and Schnorr signatures, the authors propose a hierarchical revocable authentication protocol in VANET. The proposed protocol is provably secure in the random oracle model under the Diffie‐Hellman assumption. Performance analysis illustrates that the protocol greatly saves computation resources and satisfies the well‐known security requirements. Therefore, the proposed protocol is suitable for the VANET environment.

The Internet of Things (IoT) makes our life more intelligent. Its combination with the cloud server can solve big data processing problems to meet users' needs and bring us great convenience. However, there are two challenges we need to face: data sharing and key leakage. To solve the above challenges, attribute-based encryption (ABE) is used to achieve data sharing combined with searchable encryption (SE). Most of the existing attribute-based searchable encryption (SE) schemes are inefficient and not suitable for IoT devices because of the large amount of attributes and keys. The key-leakage problem is serious in practice which very little literature focused on it. In order to address both problems, in this article, we propose a key aggregation searchable encryption (KASE) scheme based on the blockchain with auxiliary input (AI), which is capable of achieving secure data sharing on the encrypted data. Our scheme is presented through a novel chosen plaintext attack (CPA) secure scheme. We prove our scheme is chosen ciphertext attack (CCA) secure against key leakage under the decisional Diffie-Hellman assumption and Goldreich-Leivin theorem. Moreover, we adopt the proposed scheme to establish a data-sharing system based on blockchain, which improves search efficiency and connects the global ecology. In addition, extensive performance evaluations are conducted, and the results indicate our scheme is really efficient in cloud-computing-enhanced IoT.