The field of radio frequency (RF) fingerprinting and 3D object detection is experiencing significant developments, driven by the increasing demand for secure and robust sensing systems. Researchers are focusing on enhancing the security and robustness of deep learning (DL) based approaches, which have shown state-of-the-art performance in these domains. However, existing methods have been found to be vulnerable to adversarial attacks and domain shifts, highlighting the need for more robust and explainable systems. To address these challenges, researchers are exploring new approaches, such as digital twin-assisted explainable AI and perspective-invariant 3D object detection. These innovations have the potential to improve the reliability and transparency of sensing systems, enabling their widespread adoption in various applications. Notable papers in this area include:

• An Adversarial-Driven Experimental Study on Deep Learning for RF Fingerprinting, which investigates the security risks of DL-based RF fingerprinting systems.
• Digital Twin-Assisted Explainable AI for Robust Beam Prediction in mmWave MIMO Systems, which proposes a robust and explainable DL-based beam alignment engine for mmWave systems.
• Perspective-Invariant 3D Object Detection, which introduces a novel cross-platform adaptation framework for 3D object detection.
• Revisiting Physically Realizable Adversarial Object Attack against LiDAR-based Detection, which proposes a device-agnostic framework for physical adversarial object attacks.