Intelligent Sky Mirrors: SAC-Driven MF-RIS Optimization for Secure NOMA in Low-Altitude Economy

Low-altitude economy (LAE) has become a key driving force for smart cities and economic growth. To address spectral efficiency and communication security challenges in LAE, this paper investigates secure energy efficiency (SEE) maximization using intelligent sky mirrors, UAV-mounted multifunctional reconfigurable intelligent surfaces (MF-RIS) assisting nonorthogonal multiple access (NOMA) systems. These aerial mirrors intelligently amplify legitimate signals while simultaneously generating jamming against eavesdroppers. We formulate a joint optimization problem encompassing UAV trajectory, base station power allocation, RIS phase shifts, amplification factors, and scheduling matrices. Given the fractional SEE objective and dynamic UAV scenarios, we propose a two-layer optimization scheme: SAC-driven first layer for trajectory and power management, and channel alignment-based second layer for phase optimization. Simulations demonstrate that our proposed scheme significantly outperforms benchmark approaches.

A Multi-level Distillation based Dense Passage Retrieval Model

Ranker and retriever are two important components in dense passage retrieval. The retriever typically adopts a dual-encoder model, where queries and documents are separately input into two pre-trained models, and the vectors generated by the models are used for similarity calculation. The ranker often uses a cross-encoder model, where the concatenated query-document pairs are input into a pre-trained model to obtain word similarities. However, the dual-encoder model lacks interaction between queries and documents due to its independent encoding, while the cross-encoder model requires substantial computational cost for attention calculation, making it difficult to obtain real-time retrieval results. In this paper, we propose a dense retrieval model called MD2PR based on multi-level distillation. In this model, we distill the knowledge learned from the cross-encoder to the dual-encoder at both the sentence level and word level. Sentence-level distillation enhances the dual-encoder on capturing the themes and emotions of sentences. Word-level distillation improves the dual-encoder in analysis of word semantics and relationships. As a result, the dual-encoder can be used independently for subsequent encoding and retrieval, avoiding the significant computational cost associated with the participation of the cross-encoder. Furthermore, we propose a simple dynamic filtering method, which updates the threshold during multiple training iterations to ensure the effective identification of false negatives and thus obtains a more comprehensive semantic representation space. The experimental results over two standard datasets show our MD2PR outperforms 11 baseline models in terms of MRR and Recall metrics.