7 August 2023 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Automatic modulation classification (AMC) is an important technology for the monitoring, management, and control of communication systems. In recent years, machine learning approaches are becoming popular to improve the effectiveness of AMC for radio signals. However, the automatic modulation open-set recognition (AMOSR) scheme that aims to identify the known modulation types and recognize the unknown modulation signals is not well studied. Therefore, in this paper, we propose a novel multi-modal marginal prototype framework for radio frequency (RF) signals ( MMPRF ) to improve AMOSR performance. First, MMPRF addresses the problem of simultaneous recognition of closed and open sets by partitioning the feature space in the way of one versus other and marginal restrictions. Second, we exploit the wireless signal domain knowledge to extract a series of signal-related features to enhance the AMOSR capability. In addition, we propose a GAN-based unknown sample generation strategy to allow the model to understand the unknown world. Finally, we conduct extensive experiments on several publicly available radio modulation data, and experimental results show that our proposed MMPRF outperforms the state-of-the-art AMOSR methods.
11 October 2021 in IEEE Transactions on Knowledge and Data Engineering
In recent years, a surging number of unmanned aerial vehicles (UAVs) are pervasively utilized in many areas. However, the increasing number of UAVs may cause privacy and security issues such as voyeurism and espionage. It is critical for individuals or organizations to manage their behaviors and proactively prevent the misbehaved invasion of unauthorized UAVs through effective anomaly detection. The UAV anomaly detection framework needs to cope with complex signals in noisy-prone environments and to function with very limited labeled samples. This paper proposes BISSIAM, a novel framework that is capable of identifying UAV presence, types, and operation modes. BISSIAM converts UAV signals to bispectrum as the input and exploits a siamese network-based contrastive learning model to learn the vector encoding. A sampling mechanism is proposed for optimizing the sample size involved in the model training whilst ensuring the model accuracy without compromising the training efficiency. Finally, we present a similarity-based fingerprint matching mechanism for detecting unseen UAVs without the need of retraining the whole model. Experimental results show that our approach outperforms other baselines and can reach 92.85% accuracy of UAV type detection in unsupervised learning scenarios, and 91.4% accuracy for detecting the UAV type of the out-of-sample UAVs.
23 April 2024 in IEEE Transactions on Vehicular Technology
The development of technologies in the smart home provides convenience to our living life, however, the resourceconstrained characteristics lead to its frequent exposure to various attacks. Previous techniques for attack detection in the Internet of Things (IoT) are primarily fitted to simple attacks (i.e., single-step attack) but are insufficient analysis for dynamic detection of so-called complicated attacks (i.e., multistep attacks). Usually, there are three challenges for deploying a multi-step attack prediction system under IoT: 1) resourceconstrained, 2) frequently unknown multi-step threats, and 3) high demand for real-time. To address these challenges, in this paper, we propose a multi-step attack prediction architecture (namely, MS-ZeroWall) applied in the smart home. Firstly, the MS-ZeroWall does not need expensive software, which can be easily deployed on resource-constrained IoT. Then, it captures the characteristics of known threats through the variational autoencoder (VAE) and uses a VAE-based dual-domain defense strategy (DVAE) to achieve unknown multi-step threat identification. In addition, MS-ZeroWall automatically model any multi-step attack by combining the hidden Markov model (HMM) and VAE, and it uses an aggregated HMM (AHMM) approach to improve the multi-step attacks prediction under low time-delay windows so as to satisfy real-time. We evaluate the MS-ZeroWall on a publicly available multi-step attack dataset, with an F 1- score of over 0.96 on unknown multi-step threat identification, and an average accuracy improvement of 12.3% on low-latency multi-step attack prediction.
28 July 2025 in IEEE Transactions on Cognitive Communications and Networking
In recent years, deep learning (DL) techniques have been extensively utilized for specific emitter identification through the extraction of RF fingerprints. A significant challenge that DL models face in real-world scenarios is the continuous emergence of new wireless devices, such as unknown drones that suddenly appear in the sky. In these situations, the radio monitoring system must be capable of detecting these unknown devices (open-set recognition) and incrementally updating the DL model’s knowledge using only a few captured samples. This requirement presents two main challenges: 1) Incremental updates from few-shot samples can lead to catastrophic forgetting and overfitting in DL models; 2) Constructing reliable open-set thresholds for new devices with few-shot samples is difficult. To address these challenges, we propose a novel few-shot open-set incremental learning (FSOSIL) framework through meta-learning for RF fingerprint recognition, named Meta–RFF. The core idea of Meta–RFF is to simulate few-shot incremental learning and open-set recognition scenarios by constructing numerous pseudo-FSOSIL tasks and meta-training them. To enhance the open-set recognition capability, we design RF feature augmentation, open loss, and adaptive open-set thresholding modules. The algorithm’s effectiveness is validated on the large-scale aircraft recognition dataset (ADS-B), showing an improvement in closed-set accuracy and open-set AUROC of the new class by approximately 10-20% compared to other algorithms with 1-shot. We also demonstrate the algorithm’s effectiveness in a real-world test bed.
9 May 2024 in IEEE Intelligent Systems
Advanced communication systems and military reconnaissance are increasingly prevalent in high-tech environments, greatly supported by the flourishing in signal processing technologies. The recent exponential proliferation of sensors led to an unprecedented expansion in the scale and diversity of signals across various modalities. Such influx poses significant challenges in effectively integrating multi-modal signal data to deliver comprehensive and interpretive solutions across a diverse range of applications. In this paper, we provide an overview of the core issues, challenges, and future research directions in different stages of developing large-scale multi-modal signal processing models. Additionally, we introduce a prior investigation into signal representation learning, where we propose a contrastive learning-based framework to extract fine-grained signal features under few-shot conditions. Our proposed framework achieves a 24.1% performance improvement over baseline approaches, consistently demonstrating superiority over state-of-the-art methods. The code is accessible in this repository: https://github.com/YYH211/LSM .
24 October 2024 in IEEE Internet of Things Journal
Industrial cyber-physical systems (ICPS) have significantly improved production efficiency, e.g., Siemens applied ICPS in its Amberg factory, which achieved 75% production automation. However, the security problems involved have not been completely solved, e.g., the source Location privacy (SLP). Currently, with the expansion of the ICPS network size and the increasing number of devices, the existing defense process uses these device nodes as false nodes to enhance the security of the ICPS. However, this approach also results in additional energy consumption and transmission delays. To address the above challenges, we propose a solution to mix false sources and phantom strategies (i.e., Phantom-backbone-Fake, PBF). Firstly, a relay phantom node selection algorithm is proposed because adversaries are prone to track source nodes through fixed routes. We aim to optimize the path from the source node to the relay node and then to the sink node to minimize transmission delays. Ultimately, we devise a comprehensive strategy that considers both energy efficiency and distance indicators for the selection of appropriate false nodes. Through simulation and analysis, we demonstrate that our approach improves security and overall network performance.