We consider the problem of hiding wireless communications from an eavesdropper that employs a deep learning (DL) classifier to detect whether any transmission of interest is present or not. There exists one transmitter that transmits to its receiver in the presence of an eavesdropper, while a cooperative jammer (CJ) transmits carefully crafted adversarial perturbations over the air to fool the eavesdropper into classifying the received superposition of signals as noise. The CJ puts an upper bound on the strength of perturbation signal to limit its impact on the bit error rate (BER) at the receiver. We show that this adversarial perturbation causes the eavesdropper to misclassify the received signals as noise with high probability while increasing the BER only slightly. On the other hand, the CJ cannot fool the eavesdropper by simply transmitting Gaussian noise as in conventional jamming and instead needs to craft perturbation signals built by adversarial machine learning to enable covert communications. Our results show that signals with different modulation types and eventually 5G communications can be effectively hidden from an eavesdropper even if it is equipped with a DL classifier to detect transmissions.
On Privacy, Security, and Trustworthiness in Distributed Wireless Large AI Models (WLAM)
College of Information Science and Electronic Engineering, Zhejiang University（浙江大学信息科学与电子工程学院）；Key Laboratory of Information Processing, Communication and Networking of Zhejiang Province (IPCAN)（浙江省信息处理、通信与网络重点实验室）；National Mobile Communications Research Laboratory, Southeast University（东南大学国家移动通信重点实验室）；School of Information and Communication Engineering, Beijing University of Posts and Communications（北京邮电大学信息与通信工程学院）；Department of Electronic Engineering, Tsinghua University（清华大学电子工程系）；Center for 6G Technology, Khalifa University of Science and Technology（哈利法科技大学6G技术中心）
Intellicise Wireless Networks Meet Agentic AI: A Security and Privacy Perspective
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（北京邮电大学网络与交换技术全国重点实验室）；Department of Computer Science, University of Exeter（埃克塞特大学计算机科学系）；Research Institute, China United Network Communications Corporation（中国联合网络通信集团有限公司研究院）；GIC & 6GIC, Institute for Communication Systems (ICS), University of Surrey（萨里大学通信系统研究所（ICS）5GIC与6GIC）
Leveraging Channel Noise for Sampling and Privacy via Quantized Federated Langevin Monte Carlo
对于人工智能的工程应用，贝叶斯学习比标准频率论学习具有显著的优势，包括量化不确定性的能力。Langevin Monte Carlo（LMC）是一种有效的基于梯度的近似贝叶斯学习策略，其目的是从模型参数的后验分布中产生样本。先前的工作集中在通过模拟调制的多址无线信道上的LMC的分布式实现。相比之下，本文提出了量化联邦LMC（FLMC），它集成了一位随机量化的局部梯度与通道驱动的采样。随机驱动采样利用信道噪声来促进蒙特卡罗采样，同时也起到隐私机制的作用。模拟和数字实现的无线LMC比较作为一个功能的差分隐私（DP）的要求，揭示了后者在足够高的信噪比的优势。
Secure Intellicise Wireless Network: Agentic AI for Coverless Semantic Steganography Communication
State Key Laboratory of Networking and Switching Technology, Beijing University of Posts and Telecommunications（北京邮电大学网络与交换技术国家重点实验室）；ZGC Institute of Ubiquitous-X Innovation and Applications（ZGC泛在X创新与应用研究院）；Beijing Key Laboratory of 6G DOICT converged and Cloud-Native Mobile Information Networks（6G DOICT融合与云原生移动信息网络北京市重点实验室）；GIC & 6GIC, Institute for Communication Systems (ICS), University of Surrey（萨里大学通信系统研究所（ICS）5GIC与6GIC）
