Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Log inSign up
Challenges
Datasets
Workspaces
Papers
Discussions
Leaderboard
Blog
Job Board
Q3AS

© 2026 Aqora Quantum S.A.S.

TermsPrivacyLegal Notice

Optics Continuum

Deep learning for eavesdropper detection in free-space optical ON-OFF keying

Nicholas J. Savino, Sanjaya Lohani, Ryan T. Glasser

Published Oct 31, 2022• 8 citations
Publisher

Abstract

We demonstrate the efficacy of machine learning techniques in the detection of an eavesdropper in a free-space optical (FSO) communications setup. Experimentally, we use ON-OFF keying (OOK) and send strings of random bits through strong turbulence. When we apply a simulated eavesdropper to the bits in the post processing stage, a deep learning convolutional neural network (CNN) is able to successfully detect whether or not the eavesdropper is present. We vary the strength and duration of the attenuation of the simulated eavesdropper, and vary the signal-to-noise ratio (SNR) of the bit streams, and find that the strength of the eavesdropper has the greatest effect on eavesdropper detection accuracy. We are hopeful this flexible approach may be used in current and future operational FSO communications systems.

DOI
10.1364/optcon.451308

Related papers

Simulated Eavesdropper Detection in Free-Space Optics ON-OFF Keying with Deep Learning

Nicholas J. Savino, Sanjaya Lohani, Ryan T. Glasser

We use a deep learning neural network to successfully indicate when an eavesdropper is present in a free-space optics ON-OFF keying communication scheme, in which the bit stream has passed through turbulence.

Frontiers in Optics•Jan 1, 2020•0 citations

Physical-Layer Security in Free-Space Optical Communications

F. Javier López‐Martínez, Gerardo Gómez, José María Garrido-Balsells

The communication between two legitimate peers in the presence of an external eavesdropper is studied from a physical-layer security perspective in the context of free-space optical (FSO) communications. We discuss viable mechanisms to eavesdrop the communication and study the effect of random optical irradiance fluctuations inherent to FSO communications on the probability of achieving a secure transmission. We observe that the joint effect of laser-beam divergence and turbulence-induced fading on the received irradiance, under certain conditions, allows an external eavesdropper close to the legitimate receiver to compromise the communication. Interestingly, we also observe that an eavesdropper placed close to the legitimate transmitter can easily compromise the communication by taking advantage of the larger attenuation suffered by the signal when propagating through the FSO link.

IEEE photonics journal•Feb 10, 2015•252 citations

Secrecy Outage Performance in Free Space Optical Communication Links

Aanchal Gupta, Divya Dhawan, Neena Gupta

Free space optical (FSO) communication is widely used wireless type of communication, which is highly advantageous as it offers huge capacity, immunity to electromagnetic interference, and low deployment cost. FSO systems are vulnerable to eavesdropping attacks due to the miniaturization and lightweight of optical devices used for detection. Therefore, secure communication of FSO systems remains a challenging task. In order to overcome this problem, secrecy outage probability (SOP) is analyzed in this study. A system model is presented comprising a transmitter and receiver, Alice and Bob and a malicious eavesdropper, Eve. Simulation results are demonstrated which reveal that for a fixed value of Eve’s signal-to-noise ratio (SNR), the SOP decreases with increasing values of Bob’s SNR. In addition, it is shown that increasing the values of coupling parameter deteriorates the SOP performance.

CRC Press eBooks•May 28, 2024•0 citations

Coherent optical communications enhanced by machine intelligence

Sanjaya Lohani, Ryan T Glasser

Abstract Accuracy in discriminating between different received coherent signals is integral to the operation of many free-space communications protocols, and is often difficult when the receiver measures a weak signal. Here we design an optical communication scheme that uses balanced homodyne detection in combination with an unsupervised generative machine learning and convolutional neural network (CNN) system, and demonstrate its efficacy in a realistic simulated coherent quadrature phase shift keyed (QPSK) communications system. Additionally, we design the neural network system such that it autonomously learns to correct for the noise associated with a weak QPSK signal, which is distributed to the receiver prior to the implementation of the communications. We find that the scheme significantly reduces the overall error probability of the communications system, achieving the classical optimal limit. We anticipate that these results will allow for a significant enhancement of current classical and quantum coherent optical communications technologies.

arXiv:1909.02525•Machine Learning Science and Technology•Jun 12, 2020•10 citations

Experimental demonstration of deep-learning-enabled adaptive optics

Hao-Bin Fu, Zu-Yang Wan, Yu-Huai Li +9 more

Satellite-based quantum communication is a promising approach for establishing global-scale quantum networks. In free-space quantum channels, single-mode-fiber coupling plays a crucial role in increasing the signal-to-noise ratio of daylight quantum key distribution (QKD) and ensuring compatibility with standard fiber-based QKD protocols. However, consistently achieving high efficiency and stable single-mode-fiber coupling under strong atmospheric turbulence remains an ongoing experimental challenge. In this study, we experimentally demonstrate an adaptive method based on convolutional neural networks capable of directly estimating phase information from a single defocused image. We developed a convolutional neural network to establish the relationship between intensity distribution and phase information of turbulent distortions. We demonstrate the real-time performance of our deep-learning adaptive method in increasing single-mode-fiber coupling efficiency across various turbulence scales and quantify turbulence frequencies. Notably, the method proved highly effective in strong-turbulence scenarios, with frequencies reaching up to 200 Hz, leading to a significant increase in single-mode-fiber coupling efficiency. We demonstrate the corrective capability of our adaptive method for strong turbulence, enabled by the generalization of the convolutional neural network. Our results offer an efficient solution for daytime free-space QKD applications.

Physical Review Applied•Sep 19, 2024•9 citations

Information Theoretic Study of Friendly Jammer Abating an Eavesdropper in FSO Communication

Isha Chauhan, Manav R. Bhatnagar

This work is concerned with the physical layer security of the free space optical (FSO) communication network comprising of a transmitter, a receiver, an eavesdropper (Eve), and a friendly reactive jammer that aims to thwart the activity of the Eve. As the key feature of this work, we calculate the discrete-input-continuous-output for memory-less channel (DCMC) capacity of the authentic and eavesdropping channel in the presence of the atmospheric turbulence characterised by$\alpha -\mu $probability density function (PDF), zero and non-zero boresight pointing error, and partial band or broadband jamming noise. For this purpose, novel PDFs for all-encompassing conditions of FSO channel and the received signals at different nodes of the considered system are formulated. Thereafter, we devise schemes to wane the effect of a vicious Eve by formulating novel closed-form expressions of average secrecy capacity for both strategies. Our derived analytical expressions can be used as tools to examine the DCMC capacity and secrecy capacity for different turbulence regimes of FSO link, severity of boresight errors, and activity of a friendly jammer. The mathematical results are affirmed by Monte-Carlo simulation. We exhibit that deploying a friendly jammer to assist enhancing the security of an FSO system is very conducive as it makes the Eve to hike its signal-to-jamming-noise ratio by almost 10 dB when the jammer’s activity increases from 10% to 100% of the time frame of data transmission.

IEEE Transactions on Communications•Dec 12, 2023•8 citations
We demonstrate the efficacy of machine learning techniques in the detection of an eavesdropper in a free-space optical (FSO) communications setup. Experimentally, we use ON-OFF keying (OOK) and send strings of random bits through strong turbulence. When we apply a simulated eavesdropper to the bits in the post processing stage, a deep learning convolutional neural network (CNN) is able to successfully detect whether or not the eavesdropper is present. We vary the strength and duration of the attenuation of the simulated eavesdropper, and vary the signal-to-noise ratio (SNR) of the bit streams, and find that the strength of the eavesdropper has the greatest effect on eavesdropper detection accuracy. We are hopeful this flexible approach may be used in current and future operational FSO communications systems.
The communication between two legitimate peers in the presence of an external eavesdropper is studied from a physical-layer security perspective in the context of free-space optical (FSO) communications. We discuss viable mechanisms to eavesdrop the communication and study the effect of random optical irradiance fluctuations inherent to FSO communications on the probability of achieving a secure transmission. We observe that the joint effect of laser-beam divergence and turbulence-induced fading on the received irradiance, under certain conditions, allows an external eavesdropper close to the legitimate receiver to compromise the communication. Interestingly, we also observe that an eavesdropper placed close to the legitimate transmitter can easily compromise the communication by taking advantage of the larger attenuation suffered by the signal when propagating through the FSO link.
Free space optical (FSO) communication is widely used wireless type of communication, which is highly advantageous as it offers huge capacity, immunity to electromagnetic interference, and low deployment cost. FSO systems are vulnerable to eavesdropping attacks due to the miniaturization and lightweight of optical devices used for detection. Therefore, secure communication of FSO systems remains a challenging task. In order to overcome this problem, secrecy outage probability (SOP) is analyzed in this study. A system model is presented comprising a transmitter and receiver, Alice and Bob and a malicious eavesdropper, Eve. Simulation results are demonstrated which reveal that for a fixed value of Eve’s signal-to-noise ratio (SNR), the SOP decreases with increasing values of Bob’s SNR. In addition, it is shown that increasing the values of coupling parameter deteriorates the SOP performance.
Abstract Accuracy in discriminating between different received coherent signals is integral to the operation of many free-space communications protocols, and is often difficult when the receiver measures a weak signal. Here we design an optical communication scheme that uses balanced homodyne detection in combination with an unsupervised generative machine learning and convolutional neural network (CNN) system, and demonstrate its efficacy in a realistic simulated coherent quadrature phase shift keyed (QPSK) communications system. Additionally, we design the neural network system such that it autonomously learns to correct for the noise associated with a weak QPSK signal, which is distributed to the receiver prior to the implementation of the communications. We find that the scheme significantly reduces the overall error probability of the communications system, achieving the classical optimal limit. We anticipate that these results will allow for a significant enhancement of current classical and quantum coherent optical communications technologies.
Satellite-based quantum communication is a promising approach for establishing global-scale quantum networks. In free-space quantum channels, single-mode-fiber coupling plays a crucial role in increasing the signal-to-noise ratio of daylight quantum key distribution (QKD) and ensuring compatibility with standard fiber-based QKD protocols. However, consistently achieving high efficiency and stable single-mode-fiber coupling under strong atmospheric turbulence remains an ongoing experimental challenge. In this study, we experimentally demonstrate an adaptive method based on convolutional neural networks capable of directly estimating phase information from a single defocused image. We developed a convolutional neural network to establish the relationship between intensity distribution and phase information of turbulent distortions. We demonstrate the real-time performance of our deep-learning adaptive method in increasing single-mode-fiber coupling efficiency across various turbulence scales and quantify turbulence frequencies. Notably, the method proved highly effective in strong-turbulence scenarios, with frequencies reaching up to 200 Hz, leading to a significant increase in single-mode-fiber coupling efficiency. We demonstrate the corrective capability of our adaptive method for strong turbulence, enabled by the generalization of the convolutional neural network. Our results offer an efficient solution for daytime free-space QKD applications.
This work is concerned with the physical layer security of the free space optical (FSO) communication network comprising of a transmitter, a receiver, an eavesdropper (Eve), and a friendly reactive jammer that aims to thwart the activity of the Eve. As the key feature of this work, we calculate the discrete-input-continuous-output for memory-less channel (DCMC) capacity of the authentic and eavesdropping channel in the presence of the atmospheric turbulence characterised by$\alpha -\mu $probability density function (PDF), zero and non-zero boresight pointing error, and partial band or broadband jamming noise. For this purpose, novel PDFs for all-encompassing conditions of FSO channel and the received signals at different nodes of the considered system are formulated. Thereafter, we devise schemes to wane the effect of a vicious Eve by formulating novel closed-form expressions of average secrecy capacity for both strategies. Our derived analytical expressions can be used as tools to examine the DCMC capacity and secrecy capacity for different turbulence regimes of FSO link, severity of boresight errors, and activity of a friendly jammer. The mathematical results are affirmed by Monte-Carlo simulation. We exhibit that deploying a friendly jammer to assist enhancing the security of an FSO system is very conducive as it makes the Eve to hike its signal-to-jamming-noise ratio by almost 10 dB when the jammer’s activity increases from 10% to 100% of the time frame of data transmission.