The Internet of Drones (IoD) has emerged as a critical extension of the Internet of Things, enabling unmanned aerial vehicles to support diverse applications, including precision agriculture, logistics, disaster monitoring, and security surveillance. Despite its rapid growth, securing IoD communications remains a significant challenge due to the open wireless environment, high drone mobility, and strict computational and energy constraints. Existing authentication mechanisms either rely on computationally expensive cryptographic operations or remain validated only at the protocol or simulation level, leaving a critical gap in practical, hardware-validated solutions suitable for resource-constrained drone platforms. This gap motivates the need for a lightweight, privacy-preserving authentication scheme that is both theoretically sound and experimentally deployable on real hardware. To address this, we propose a Physically Unclonable Functions (PUF)-assisted lightweight authentication scheme for IoD environments that binds cryptographic keys to each drone’s intrinsic hardware characteristics via PUFs. The scheme employs dynamically generated pseudo-identities to conceal permanent drone identities and prevent tracking, while authentication and key agreement are achieved using efficient symmetric cryptographic primitives, including SHA-256 for key derivation and updates, AES-256 for secure communication, and lightweight XOR operations to minimize overhead. Forward secrecy is ensured through rolling key updates, and periodic renewal of PUF challenges enhances resistance to replay and modeling attacks. To validate practicality, both software-based and hardware-based implementations were developed and evaluated. The software evaluation demonstrates a low communication overhead of 708.5 bytes and an average computation time of 18.87 ms. The hardware implementation on a Nexys A7-100T FPGA operates at 100 MHz with only 12.49% LUT utilization and low dynamic power consumption of approximately 182.5 mW. These results confirm that the proposed framework achieves an effective balance between security, privacy, and efficiency. The significance of this work lies in providing a fully hardware-validated, PUF-based authentication framework specifically tailored to the real-world constraints of IoD environments, offering a practical foundation for securing next-generation drone networks.

Vision–Language Navigation (VLN) requires embodied agents to interpret natural-language instructions in 3D environments. While significant progress has been made, state-of-the-art agents often struggle with instructions that demand fine-grained visual understanding, correctly grounding specific object attributes, distinguishing between similar objects, and interpreting complex spatial relationships. Many methods rely on static visual features or on global cross-modal attention and lack mechanisms to dynamically resolve ambiguities during navigation. We propose DyGRAV (Dynamic Grounding and Relational Reasoning for VLN), which is a dynamic, uncertainty-aware framework that augments a strong VLN backbone with two adaptively triggered reasoning modules. The Contextual VLM Querying module detects grounding ambiguity for descriptive phrases (e.g., “the ceramic bowl”) and issues targeted queries to a vision–language model (e.g., CLIP) using current visual evidence, while the Incremental Relational Scene Graph (IRSG) constructs lightweight, task-relevant relational memory online to resolve complex spatial relations (e.g., “the chair next to the window”). A budget-aware gating mechanism regulates when these modules are invoked, optimizing the balance between reasoning quality and computational cost through value-per-cost selection and hard budget constraints. Comprehensive evaluations on R2R and RxR, along with a fine-grained diagnostic benchmark emphasizing attribute and relation understanding, show that DyGRAV achieves superior navigation accuracy on challenging instructions while maintaining bounded per-step compute budgets with 97.33% episode-level adherence.

This paper presents a CLIP-based unsupervised learning method for annotation-free multi-label image classification, including three stages: initialization, training, and inference. At the initialization stage, we take full advantage of the powerful CLIP model and propose a novel approach to extend CLIP for multi-label predictions based on global-local image-text similarity aggregation. To be more specific, we split each image into snippets and leverage CLIP to generate the similarity vector for the whole image (global) as well as each snippet (local). Then a similarity aggregator is introduced to leverage the global and local similarity vectors. Using the aggregated similarity scores as the initial pseudo labels at the training stage, we propose an optimization framework to train the parameters of the classification network and refine pseudo labels for unobserved labels. During inference, only the classification network is used to predict the labels of the input image. Extensive experiments show that our method outperforms state-of-the-art unsupervised methods on MS-COCO, PASCAL VOC 2007, PASCAL VOC 2012, and NUS datasets and even achieves comparable results to weakly supervised classification methods.