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

IEEE International Conference on Communications workshops

Adversarial Learning for Advantage Distillation in Secret Key Agreement Over UWAC

Francesco Ardizzon, Amedeo Giuliani, Nicola Laurenti, Stefano Tomasin

Published May 28, 2023• 2 citations
Publisher

Abstract

Underwater acoustic communications (UWACs) are being adopted in several applications, and their security mechanisms require periodically renewed symmetric keys among legitimate devices. To this end, a secret key agreement (SKA) exploiting the UWAC context can be implemented. In this paper, we focus on one step of the source-based SKA protocol, i.e., the advantage distillation, when the legitimate users pre-process the channel measurement to increase the agreement while decreasing the attacker's knowledge about the key. We propose to learn the advantage distillation process by using a dataset of observed channels from the legitimate parties and the attacker, respectively. In turn, also the attacker uses such data to extract the key from its own underwater channel observations. The key extraction functions are derived through a computationally efficient data-driven adversarial strategy based on a metric related to the secret key rate that can be computed with a lower computational cost. The proposed strategy is tested considering experimental UWAC data, derived from a sea experiment. Results prove the quick convergence of the algorithm and the advantage of using the proposed techniques.

DOI
10.1109/iccworkshops57953.2023.10283582

Related papers

ML-Based Advantage Distillation for Key Agreement in Underwater Acoustic Channels

Amedeo Giuliani, Francesco Ardizzon, Stefano Tomasin

Underwater networks have become an important topic of research due to their potential impact on several military and civil applications. To secure these communications, many protocols require the users to have symmetric secret keys. To distribute the keys, we can resort to physical layer key generation schemes, where the keys are generated by each user from the channel itself, by exploiting the environment as a source of randomness. We focus on the advantage distillation step of the secret key agreement (SKA) procedure, where the users extract the bit sequence from the channel observations. We propose an adversarial autoencoder (AAE) model for advantage distillation, which has multiple tasks: it enhances the reciprocity between legitimated channel features, decreases the reciprocity to the attacker channel features, and provides uniformly distributed bit sequences. The proposed approach is adaptive and directly derived from the training dataset, thus it does not require the a priori knowledge of the channel statistics. The solution is tested using channel observations collected from a sea experiment and compared to existing advantage distillation solutions, showing a significant improvement over the state of the art.

IEEE International Conference on Communications workshops•May 28, 2023•5 citations

Advantage-Distillation Strategies with Side Information for Underwater Acoustic Channels

Francesco Ardizzon, Francesco Giurisato, Stefano Tomasin

Many military and civil applications using underwater acoustic channels (UWACs) are paired with security services, providing, for instance, secrecy and authenticity to the communication.These mechanisms however often require periodically renewed symmetric keys among two communicating devices, namely Alice and Bob.To this end, secret keys can be agreed upon using the physicallayer communication channel, leveraging, in particular, the reciprocity and randomness of the UWAC to extract a common key that remains secret to an attacker (Eve).In this paper, we propose a novel solution for the advantagedistillation part of the secret key generation procedure.After channel probing, the advantage of distillation lets Alice and Bob extract a sequence of bits from their own (analog) measurements.We propose an asymmetric advantage-distillation protocol with two novel features: i) the quantizers used by Alice and Bob are derived maximizing the secret key capacity cooperating through a public channel and ii) Alice transmits a correction over a public authenticated side channel.Numerical results prove the effectiveness of our approach, showing that exchanging a few bits of information before information reconciliation allows extracting more secret bits from the channel.

Convention of the European Acoustics Association Forum Acusticum•Jan 17, 2024•0 citations

Secret-Key-Agreement Advantage Distillation With Quantization Correction

Francesco Ardizzon, Francesco Giurisato, Stefano Tomasin

We consider a physical layer-based secret-key-agreement (SKA) scenario where Alice and Bob aim at extracting a common bit sequence, which should remain secret to Eve, by quantizing a random number obtained from measurements of their communication channel. We propose an asymmetric advantage distillation protocol where i) Alice quantizes her measurement and sends partial information on it over an authenticated public side channel, and ii) Bob (and Eve) quantizes his measurement by exploiting the partial information. The partial information on the position of the measurement in the quantization interval allows Bob to obtain a quantized value closer to that of Alice. Such strategies are shown to increase the lower bound of the secret key rate.

arXiv:2304.10312•IEEE Communications Letters•Aug 1, 2023•7 citations

Learning-Based Secret Key Generation in Relay Channels Under Adversarial Attacks

Mehdi Letafati, Hamid Behroozi, Babak Hossein Khalaj +1 more

Wireless secret key generation (WSKG) facilitates efficient key agreement protocols for securing the sixth generation (6G) wireless networks thanks to its inherently lightweight functionality. Nevertheless, with the existence of adversarial attacks or internal impairments, WSKG can be negatively affected during the randomness distillation, where the legitimate parties measure a source of common randomness. In this paper, we propose a learning-aided approach for cooperative WSKG under man-in-the-middle (MitM) adversarial attack, while the legitimate nodes suffer fromhardware impairments(HIs). The key idea is to process the PHY-attribute data on the application layer via deploying a deep neural network (DNN) to enhance the randomness distillation. This way, we realize a learning-based software-centric security solution. More specifically, we take into account the sequence-type nature of observed data, and propose a DNN comprised ofgated recurrent units(GRUs) to learn the sequence of observations at legitimate endpoints, while the MitM is also alleviated. Our numerical results verify the performance gain of the proposed learning-based approach compared with the state-of-the-arts. Moreover, time and computation complexity of different learning-based models are studied to address the complexity-performance trade-off. Our tests highlight a performance gain of about 43% in terms of mean-square error (MSE) in comparison with a conventional PHY-only scheme.

IEEE Open Journal of Vehicular Technology•Jan 1, 2023•9 citations

New Secret Key Agreement Scheme over Relay Communication Channel

Lijuan Xing, Feng Pan, Xueqin Jiang +2 more

Abstract The novel advantage distillation (AD) scheme for secret key agreement (SKA) scheme over relay communication system for the wiretap channel model is proposed. For the case where there are noiseless both the main channel and the eavesdropper’s channel, the SKA scheme for the noiseless relay communication (SKA-NRC) system is proposed. In this scheme, random sequences qA and qB are used as artificial interference to prevent eavesdropping. Simulation results show that with the proposed SKA schemes, the bit error ratio (BER) of eavesdropper Eve maintains stably at 0.5, while legitimate users Alice and Bob are able to get much lower BERs.

Journal of Physics Conference Series•Jan 1, 2020•0 citations

An Efficient Advantage Distillation Scheme for Bidirectional Secret-Key Agreement

Yan Feng, Xueqin Jiang, Jia Hou +2 more

The classical secret-key agreement (SKA) scheme includes three phases: (a) advantage distillation (AD), (b) reconciliation, and (c) privacy amplification. Define the transmission rate as the ratio between the number of raw key bits obtained by the AD phase and the number of transmitted bits in the AD. The unidirectional SKA, whose transmission rate is 0 . 5, can be realized by using the original two-way wiretap channel as the AD phase. In this paper, we establish an efficient bidirectional SKA whose transmission rate is nearly 1 by modifying the two-way wiretap channel and using the modified two-way wiretap channel as the AD phase. The bidirectional SKA can be extended to multiple rounds of SKA with the same performance and transmission rate. For multiple rounds of bidirectional SKA, we have provided the bit error rate performance of the main channel and eavesdropper’s channel and the secret-key capacity. It is shown that the bit error rate (BER) of the main channel was lower than the eavesdropper’s channel and we prove that the transmission rate was nearly 1 when the number of rounds was large. Moreover, the secret-key capacity C s was from 0 . 04 to 0 . 1 as the error probability of channel was from 0 . 01 to 0 . 15 in binary symmetric channel (BSC). The secret-key capacity was close to 0 . 3 as the signal-to-noise ratio increased in the additive white Gaussian noise (AWGN) channel.

Entropy•Sep 18, 2017•5 citations
Underwater acoustic communications (UWACs) are being adopted in several applications, and their security mechanisms require periodically renewed symmetric keys among legitimate devices. To this end, a secret key agreement (SKA) exploiting the UWAC context can be implemented. In this paper, we focus on one step of the source-based SKA protocol, i.e., the advantage distillation, when the legitimate users pre-process the channel measurement to increase the agreement while decreasing the attacker's knowledge about the key. We propose to learn the advantage distillation process by using a dataset of observed channels from the legitimate parties and the attacker, respectively. In turn, also the attacker uses such data to extract the key from its own underwater channel observations. The key extraction functions are derived through a computationally efficient data-driven adversarial strategy based on a metric related to the secret key rate that can be computed with a lower computational cost. The proposed strategy is tested considering experimental UWAC data, derived from a sea experiment. Results prove the quick convergence of the algorithm and the advantage of using the proposed techniques.
Underwater networks have become an important topic of research due to their potential impact on several military and civil applications. To secure these communications, many protocols require the users to have symmetric secret keys. To distribute the keys, we can resort to physical layer key generation schemes, where the keys are generated by each user from the channel itself, by exploiting the environment as a source of randomness. We focus on the advantage distillation step of the secret key agreement (SKA) procedure, where the users extract the bit sequence from the channel observations. We propose an adversarial autoencoder (AAE) model for advantage distillation, which has multiple tasks: it enhances the reciprocity between legitimated channel features, decreases the reciprocity to the attacker channel features, and provides uniformly distributed bit sequences. The proposed approach is adaptive and directly derived from the training dataset, thus it does not require the a priori knowledge of the channel statistics. The solution is tested using channel observations collected from a sea experiment and compared to existing advantage distillation solutions, showing a significant improvement over the state of the art.
Many military and civil applications using underwater acoustic channels (UWACs) are paired with security services, providing, for instance, secrecy and authenticity to the communication.These mechanisms however often require periodically renewed symmetric keys among two communicating devices, namely Alice and Bob.To this end, secret keys can be agreed upon using the physicallayer communication channel, leveraging, in particular, the reciprocity and randomness of the UWAC to extract a common key that remains secret to an attacker (Eve).In this paper, we propose a novel solution for the advantagedistillation part of the secret key generation procedure.After channel probing, the advantage of distillation lets Alice and Bob extract a sequence of bits from their own (analog) measurements.We propose an asymmetric advantage-distillation protocol with two novel features: i) the quantizers used by Alice and Bob are derived maximizing the secret key capacity cooperating through a public channel and ii) Alice transmits a correction over a public authenticated side channel.Numerical results prove the effectiveness of our approach, showing that exchanging a few bits of information before information reconciliation allows extracting more secret bits from the channel.
We consider a physical layer-based secret-key-agreement (SKA) scenario where Alice and Bob aim at extracting a common bit sequence, which should remain secret to Eve, by quantizing a random number obtained from measurements of their communication channel. We propose an asymmetric advantage distillation protocol where i) Alice quantizes her measurement and sends partial information on it over an authenticated public side channel, and ii) Bob (and Eve) quantizes his measurement by exploiting the partial information. The partial information on the position of the measurement in the quantization interval allows Bob to obtain a quantized value closer to that of Alice. Such strategies are shown to increase the lower bound of the secret key rate.
Wireless secret key generation (WSKG) facilitates efficient key agreement protocols for securing the sixth generation (6G) wireless networks thanks to its inherently lightweight functionality. Nevertheless, with the existence of adversarial attacks or internal impairments, WSKG can be negatively affected during the randomness distillation, where the legitimate parties measure a source of common randomness. In this paper, we propose a learning-aided approach for cooperative WSKG under man-in-the-middle (MitM) adversarial attack, while the legitimate nodes suffer fromhardware impairments(HIs). The key idea is to process the PHY-attribute data on the application layer via deploying a deep neural network (DNN) to enhance the randomness distillation. This way, we realize a learning-based software-centric security solution. More specifically, we take into account the sequence-type nature of observed data, and propose a DNN comprised ofgated recurrent units(GRUs) to learn the sequence of observations at legitimate endpoints, while the MitM is also alleviated. Our numerical results verify the performance gain of the proposed learning-based approach compared with the state-of-the-arts. Moreover, time and computation complexity of different learning-based models are studied to address the complexity-performance trade-off. Our tests highlight a performance gain of about 43% in terms of mean-square error (MSE) in comparison with a conventional PHY-only scheme.
Abstract The novel advantage distillation (AD) scheme for secret key agreement (SKA) scheme over relay communication system for the wiretap channel model is proposed. For the case where there are noiseless both the main channel and the eavesdropper’s channel, the SKA scheme for the noiseless relay communication (SKA-NRC) system is proposed. In this scheme, random sequences qA and qB are used as artificial interference to prevent eavesdropping. Simulation results show that with the proposed SKA schemes, the bit error ratio (BER) of eavesdropper Eve maintains stably at 0.5, while legitimate users Alice and Bob are able to get much lower BERs.
The classical secret-key agreement (SKA) scheme includes three phases: (a) advantage distillation (AD), (b) reconciliation, and (c) privacy amplification. Define the transmission rate as the ratio between the number of raw key bits obtained by the AD phase and the number of transmitted bits in the AD. The unidirectional SKA, whose transmission rate is 0 . 5, can be realized by using the original two-way wiretap channel as the AD phase. In this paper, we establish an efficient bidirectional SKA whose transmission rate is nearly 1 by modifying the two-way wiretap channel and using the modified two-way wiretap channel as the AD phase. The bidirectional SKA can be extended to multiple rounds of SKA with the same performance and transmission rate. For multiple rounds of bidirectional SKA, we have provided the bit error rate performance of the main channel and eavesdropper’s channel and the secret-key capacity. It is shown that the bit error rate (BER) of the main channel was lower than the eavesdropper’s channel and we prove that the transmission rate was nearly 1 when the number of rounds was large. Moreover, the secret-key capacity C s was from 0 . 04 to 0 . 1 as the error probability of channel was from 0 . 01 to 0 . 15 in binary symmetric channel (BSC). The secret-key capacity was close to 0 . 3 as the signal-to-noise ratio increased in the additive white Gaussian noise (AWGN) channel.