UAV Individual Identification via Distilled RF Fingerprints-Based LLM in ISAC Networks

TL;DR

This paper introduces a dynamic knowledge distillation framework using a modified GPT-2-based RFF-LLM for UAV ID identification in ISAC networks, achieving high accuracy with low model complexity.

Contribution

It proposes a novel dynamic KD strategy with PPO to efficiently compress a RFF-LLM for UAV identification, enhancing accuracy and reducing model size.

Findings

Achieves 98.38% identification accuracy.

Uses only 0.15 million parameters.

Responds within 2.74 ms.

Abstract

Unmanned aerial vehicle (UAV) individual (ID) identification is a critical security surveillance strategy in low-altitude integrated sensing and communication (ISAC) networks. In this paper, we propose a novel dynamic knowledge distillation (KD)-enabled wireless radio frequency fingerprint large language model (RFF-LLM) framework for UAV ID identification. First, we propose an RFF-LLM framework based on the modified GPT-2 model to improve the identification accuracy in complex outdoor environments. Then, considering the parameter overhead of the RFF-LLM, we design a dynamic KD strategy to compress the model. Specifically, the proximal policy optimization (PPO) algorithm is employed to dynamically adjust the distillation temperature, overcoming the local optimum dilemma inherent in static KD. As a next step, the knowledge of the RFF-LLM is adequately transferred to the lightweight Lite-HRNet model. Finally, our experiments are conducted based on the self-built drone RFF dataset of Release one, namely DRFF-R1, by collecting the I/Q signals of 20 commercial UAVs in channel 149. The experiment results show that the proposed framework achieves 98.38% ID identification accuracy with merely 0.15 million parameters and 2.74 ms response time, which outperforms the benchmarks.