Tailai Wen

automatic modulation classification (AMC) plays a vital role in enhancing spectrum utilization efficiency in Cognitive Internet of Things (CIoT) scenarios. However, it introduces security vulnerabilities by enabling eavesdroppers to accurately identify modulation schemes of intercepted signals through deep neural network (DNN)-based classifiers. Considering that DNN performance is highly susceptible to adversarial examples, this work aims to design adversarial perturbations for signal transmitters to effectively prevent eavesdroppers from intercepting and identifying target user signals. Unlike image classification tasks, existing methods for generating adversarial perturbations in wireless communications face three critical limitations: 1) instability in perturbation power control; 2) vulnerability to signal filtering; and 3) high perceptibility of perturbations. To address these challenges, we reformulate the adversarial example generation problem with specific target perturbation power constraints. By jointly leveraging feature vectors from the final DNN layer and frequency-domain characteristics of transmitted signals, we propose a cross-domain power constrained adversarial attack (CPCAA) method that further optimizes perturbation generation. Experimental results demonstrate that the proposed method generates highly imperceptible adversarial examples with specified energy constraints while achieving significant attack performance, even when eavesdroppers deploy various types of filters.

Deep learning algorithms have become an essential component in the field of cognitive radio, especially playing a pivotal role in automatic modulation classification. However, Deep learning also present risks and vulnerabilities. Despite their outstanding classification performance, they exhibit fragility when confronted with meticulously crafted adversarial examples, posing potential risks to the reliability of modulation recognition results. Addressing this issue, this letter pioneers the development of an intelligent modulation classification framework based on conformal theory, named the Conformal Shield, aimed at detecting the presence of adversarial examples in unknown signals and assessing the reliability of recognition results. Utilizing conformal mapping from statistical learning theory, introduces a custom-designed Inconsistency Soft-solution Set, enabling multiple validity assessments of the recognition outcomes. Experimental results demonstrate that the Conformal Shield maintains robust detection performance against a variety of typical adversarial sample attacks in the received signals under different perturbation-to-signal power ratio conditions.

The satellite clocks carried on the BeiDou navigation System (BDS) are a self-manufactured hydrogen clock and improved rubidium clock, and their on-orbit performance and stabilities are not as efficient as GPS and Galileo satellite clocks caused of the orbital diversity of the BDS and the complexity of the space operating environment. Therefore, the existing BDS clock product cannot guarantee the high accuracy demand for precise point positioning in real-time scenes while the communication link is interrupted. To deal with this problem, we proposed a deep learning-based approach for BDS short-term satellite clock offset modeling which utilizes the superiority of Long Short-Term Memory (LSTM) derived from Recurrent Neural Networks (RNN) in time series modeling, and we call it QPLSTM. The ultrarapid predicted clock products provided by IGS (IGU-P) and four widely used prediction methods (the linear polynomial, quadratic polynomial, gray system (GM (1,1)), and Autoregressive Integrated Moving Average (ARIMA) model) are selected to compare with the QPLSTM. The results show that the prediction residual is lower than clock products of IGU-P during 6-hour forecasting and the QPLSM shows a greater performance than the mentioned four models. The average prediction accuracy has improved by approximately 79.6, 69.2, 80.4, and 77.1% and 68.3, 52.7, 66.5, and 69.8% during a 30 min and 1-hour forecasting. Thus, the QPLSTM can be considered as a new approach to acquire high-precision satellite clock offset prediction.