DPUAUT: Secure Authentication Protocol With SmartNiC Integration for Trustworthy Communications in Intelligent Swarm Systems

Swarm devices are becoming increasingly prevalent in next-generation networks because they can efficiently handle large-scale distributed computing tasks. The traditional cloud-based frameworks are not suitable for swarm devices due to their low latency and scalability requirements. Moreover, these frameworks are vulnerable to security threats when communicating over unsecured networks. Edge computing addresses these challenges, but it suffers from several security issues, such as device authentication, access control, and privacy issues for swarm devices. Many authentication protocols have been proposed to protect from these attacks, but most of them are vulnerable to physical attacks due to the keys stored in device memory. Physical Unclonable Function (PUF)s can significantly enhance the physical security of these devices by generating a unique identifier for each device, making it difficult for attackers to physically clone or impersonate these devices. In this paper, we propose a provably secure authentication protocol using a Bluefield Data Processing Unit (DPU), enabling one-round mutual authentication while preserving anonymity and preventing physical attacks using PUF. We conduct security analyses comprehensively, which provide evidence of its strong resilience against attacks. Experimental evaluation confirms its dominance over existing solutions. The DPUAUT swarm authentication protocol has a low computational overhead of
$6.161ms$
, and the communication overhead is
$1052Bits$
.