ML-Based Identification of Structured Light Schemes under Free Space Jamming Threats for Secure FSO-Based Applications

This paper exploits for the first time use of machine learning (ML) based techniques to identify complex structured light patterns under free space optics (FSO) jamming attacks secure FSO-based applications. Five M-ary modulation schemes, construed using Laguerre and Hermite Gaussian (LG HG) mode families, were used in this investigation. These include 8-ary LG, superposition-LG, 16-ary HG, LG 32-ary superposition-LG HG formats. The work was conducted experimental demonstrations two different jammer positions. convolutional neural network (CNN)-based ML method utilized differentiate between stressed patterns. results show a 100% recognition accuracy at 1, −2, −2 dB signal-to-jammer ratios (SJR), respectively. For SJR values < 0 dB, standard modes are most affected by not recommended data transmission such an environment. Besides, determining direction arrival investigated CNN simpler classifier on linear discriminant analysis (LDA). that advanced networks (e.g., CNN) required achieve reliable performance determination accuracy, −5 SJR, as opposed 97%, 2 simple LDA classifier.