*4.4. Comparative Evaluation*

Table 2 presents the comparison between our LightMAN and previous blockchainbased solutions for UAV networks. The symbol √ indicates that the scheme guarantees the security properties or implements some prototypes to evaluate the system performance or other specifications. The symbol × indicates the opposite case. Existing blockchainbased solutions that are developed to secure UAV communications [13–15] lack details on underlying blockchain frameworks, and most of them assumed that the cryptocurrencyoriented blockchain designs can be adopted in the UAV communication systems. Being fully aware of the specific performance requirements and resource constraints, we demonstrate a complete system architecture consisting of ML-based UAM monitoring and a lightweight microchain. Compared with solutions that adopt conventional PoW and BFT consensus protocols [17,19], LightMAN focuses on a lightweight blockchain design for IoD, which leverages a novel PoC+VCF consensus protocol to reduce computation and communication overheads on IoT systems. We especially evaluate blockchain performance (e.g., network latency, transaction throughput, and computation overheads) by applying a microchainenabled security mechanism to access authentication and data sharing process scenarios, which are not considered or sufficiently discussed in related work [16,18].

In terms of the optimization for UAV data storage, a DDS is adopted atop the Swarm network as the off-chain storage to store raw UAV data. Therefore, LightMAN is promising for the enhancement of the system robustness (availability and recoverability) for data-sharing applications compared with existing solutions that rely on centralized storage [19]. Furthermore, LightMAN stores encrypted sensitive information on the DDS while only recording references of raw data on the transparent distributed ledger. As a result, blockchain transactions only contain references of small size rather than large volumes of UAV data. Such a hybrid on-chain and off-chain data storage structure not only reduces communication and storage overheads but also ensures privacy preservation in the data-sharing process by exposing hash-style references as proofs.

**Table 2.** Comparison among existing solutions.


#### **5. Conclusions and Future Work**

This paper presents LightMAN, which combines DL-powered UAM security and a lightweight microchained fabric to support assurance and resilience-oriented UAM networks. The DL-based cybersecurity monitoring techniques can prevent cyber threats and provide cognitive-based decision support for UAM. A lightweight microchain works as a secure-by-design network infrastructure to enable decentralized security solutions for UAV access authentication and data sharing. The experimental results based on a prototype implementation demonstrate the effectiveness and efficiency of our LightMAN. However, there are open questions that need to be addressed before applying LightMAN to real-world UAM scenarios. We leave these limitations to our future work:


**Author Contributions:** Conceptualization, R.X., S.W., Y.C., G.C. and K.P.; methodology, R.X., S.W. and Y.C.; software, R.X. and S.W.; validation, R.X., S.W. and Y.C.; formal analysis, R.X., S.W. and Y.C.; funding acquisition, Y.C.; investigation, R.X., S.W. and Y.C.; resources, R.X., S.W. and G.C.; data curation, R.X. and S.W.; writing—original draft preparation, R.X., S.W. and Y.C.; writing—review and editing, R.X., S.W. and Y.C.; visualization, R.X. and S.W.; supervision, Y.C.; project administration, Y.C. All authors have read and agreed to the published version of the manuscript.

**Funding:** This research was partially funded by the United State National Science Foundation (NSF) under the grant CNS-2141468.

**Institutional Review Board Statement:** Not applicable.

**Informed Consent Statement:** Not applicable.

**Data Availability Statement:** Not applicable.

**Acknowledgments:** The authors want to thank Erik Blasch for his guidance and suggestions during the writing of this manuscript. The views and conclusions contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the Air Force Research Laboratory or the U.S. government.

**Conflicts of Interest:** The authors declare no conflict of interest.

#### **Abbreviations**

The following abbreviations are used in this manuscript:


#### **References**

