TrustPKBG: Trustworthy Protocol Knowledge Blueprints Generation via LLM for Low-Altitude AAV Networks

In low-altitude networks, reliable and lightweight flight interconnection among AAVs mainly depends on protocols like Message Queuing Telemetry Transport (MQTT). However, existing protocol analysis methods often fail to adapt to unknown program functions caused by version updates due to a lack of protocol knowledge blueprints (PKB). Moreover, due to the lack of multiple rounds of verification in terms of grammar semantics and execution logic representation, the correctness, validity and credibility of the generated PKB in practical scenarios remain questionable. To address these challenges, this paper proposes a novel trustworthy protocol knowledge blueprints generation (TrustPKBG) framework for low-altitude AAV networks by large language model (LLM). In TrustPKBG, a Hierarchical Chain-of-Thought (HCoT) strategy is designated to automatically transform technical specifications into a structured, objective, and consistent PKB draft against the bias of human construction. Moreover, to enhance the abstract semantic similarity between PKB drafts and RFC documents, a memory-aware multi-agent collaboration mechanism is also presented, which enables closed-loop error detection and knowledge updating. To demonstrate the superiority of TrustPKBG, we also implement a Fuzzing-based PKB Verifier over MQTT/CoAP. Experimental results demonstrate that fuzzing with TrustPKBG can achieve an average code coverage rate of 33.71% for MQTT and 33.5% for CoAP, which is 50.83% higher than the baseline average coverage rate of 22.35% for MQTT and 27.6% for CoAP, with a valid test ratio of 74.57% for MQTT and 62.3% for CoAP. Furthermore, we explore PKB’s application in protocol code auditing by evaluating open-source MQTT and CoAP implementations for compliance verification, which demonstrate the effectiveness of the proposed methods.