Driven by growing mobile traffic, millimeter wave (mmWave) communications have recently been developed to enhance wireless network capacity. Due to insufficient coverage and the lack of support for mobility, mmWave is often deployed in the ultra-dense small cells of the 5G heterogeneous network. In this article, we first summarize the characteristics of the 5G heterogeneous network from the viewpoints of devices, spectra, and networks. We then propose a triple-band network structure which incorporates licensed bands, sub-6GHz unlicensed bands, and mmWave bands to support various types of mobile users. Based on the novel network structure, we further propose a self-optimizing traffic steering strategy which can intelligently steer traffic to specific networks and spectra according to the dynamic network and traffic environments. Several use cases are also discussed to facilitate the implementation of our proposals. Finally, we present numerical results to demonstrate that the proposed network structure and strategy can effectively enhance the system throughput and energy efficiency.
With the widespread deployment of deep neural networks in real-world physical environments, assessing their robustness against adversarial attacks has become a central issue in AI safety. However, the existing two-dimensional adversarial methods often lack robustness in the physical world, while three-dimensional adversarial camouflage generation typically relies on high-fidelity 3D models, limiting practicality. To address these limitations, we propose CAM3D, a cross-domain 3D adversarial camouflage generation framework based on single-view image input. The framework establishes an inverse graphics network based on the Mamba architecture, integrating a hybrid non-causal state-space-duality module and a wavelet-enhanced dual-branch local perception module. This design preserves global dependency modeling while strengthening high-frequency detail representation, enabling high-precision recovery of 3D geometry and texture from a single image and providing a high-quality structural prior for subsequent adversarial camouflage optimization. On this basis, CAM3D employs a progressive three-stage optimization strategy that sequentially performs multi-view pseudo-supervised reconstruction, real-image detail refinement, and cross-domain adversarial camouflage generation, thereby systematically improving the attack effectiveness of adversarial camouflage in both the digital and physical domains. The experimental results demonstrate that CAM3D substantially reduces the detection performance of mainstream object detectors, and comparative as well as ablation studies further confirm its advantages in geometric consistency, texture fidelity, and physical transferability. Overall, CAM3D offers an effective paradigm for adversarial attack research in real-world physical settings, characterized by low data dependency and strong physical generalization.