The field of autonomous systems is moving towards addressing security vulnerabilities and improving navigation capabilities. Researchers are investigating the potential risks posed by Trojan attacks and hardware-level faults, and developing innovative solutions to enhance the resilience of these systems. Notably, the intersection of deep learning security and hardware-level faults is becoming a critical area of focus, particularly in applications such as medical imaging. Additionally, advancements in navigation strategies using deep reinforcement learning are paving the way for more efficient and safe autonomous vehicle operation in complex environments. Noteworthy papers include: An Experimental Study of Trojan Vulnerabilities in UAV Autonomous Landing, which demonstrates the potential security risks posed by Trojan attacks. Hammering the Diagnosis: Rowhammer-Induced Stealthy Trojan Attacks on ViT-Based Medical Imaging, which highlights the vulnerability of medical imaging systems to hardware-level attacks. FaRAccel: FPGA-Accelerated Defense Architecture for Efficient Bit-Flip Attack Resilience in Transformer Models, which proposes a novel hardware accelerator architecture for defending against bit-flip attacks. Navigation in a Three-Dimensional Urban Flow using Deep Reinforcement Learning, which develops an optimal navigation strategy for UAVs in complex urban environments.