Adversarial Networks for Secure Wireless Communications

Marchioro, Thomas; Laurenti, Nicola; Gündüz, Deniz

doi:10.1109/icassp40776.2020.9053216

Cited by 15 publications

(6 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hence, the RoI packets will require stringent security and reliability specifications, while the BG packets do not provide useful data if being revealed to the passive Eves. Remarkably, a content-based secure wireless image delivery is not addressed in many recently-published works in the area of wireless image transmission, e.g., [10], [20], [21]. In other words, they all consider a unified end-to-end approach for sending an image over the air, regardless of paying attention to the content/region of the image being transmitted at each transmission slot (TS).…”

Section: Contributionsmentioning

confidence: 99%

“…In this paper, different from the previous works of [7], [12]- [14], and [21], we take the delay limits of a practical image transmission system into account via utilizing a hybrid multi-packet transmission design. We then derive an exact closed-form expression, which was not obtained in [15]- [17], for the quality-of-security (QoSec) violating probability (QVP) as our performance metric to addresses the effect of delay limits on the image delivery.…”

Section: Contributionsmentioning

confidence: 99%

See 1 more Smart Citation

On Learning-Assisted Content-Based Secure Image Transmission for Delay-Aware Systems with Randomly-Distributed Eavesdroppers -- Extended Version

Letafati,

Behroozi,

Khalaj

et al. 2021

Preprint

View full text Add to dashboard Cite

In this paper, a learning-aided content-based wireless image transmission scheme is proposed, where a multi-antenna-aided source wishes to securely deliver an image to a legitimate destination in the presence of randomly distributed eavesdroppers (Eves). We take into account the fact that not all regions of an image have the same importance from the security perspective. Hence, we propose a transmission scheme, where the source employs a hybrid method to realize both the error-free data delivery of public regions-containing less-important pixels; and an artificial noise (AN)-aided transmission scheme to provide security for the regions containing large amount of information. Moreover, in order to reinforce system's security, fountain-based packet delivery is adopted: First, the source node encodes image packets into fountain-like packets prior to sending them over the air. The secrecy of our proposed scheme will be achieved if the legitimate destination correctly receives the entire image source packets, while conforming to the latency limits of the system, before Eves can obtain the important regions.Accordingly, the secrecy performance of our scheme is characterized by deriving the closed-form expression for the quality-of-security (QoSec) violation probability. Moreover, our proposed wireless image delivery scheme leverages the deep neural network (DNN) and learns to maintain optimized transmission parameters, while achieving a low QoSec violation probability. Simulation results are provided with some useful engineering insights which illustrate that our proposed learning-assisted

show abstract

Section: Contributionsmentioning

confidence: 99%

Section: Contributionsmentioning

confidence: 99%

On Learning-Assisted Content-Based Secure Image Transmission for Delay-Aware Systems with Randomly-Distributed Eavesdroppers -- Extended Version

Letafati,

Behroozi,

Khalaj

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Similar data-driven wiretap channel approaches have recently been proposed for Gaussian channels in [16][17][18][19]. However, [16,18,19] focus on channel coding, and [18,19] enforce coding structure to the encoder, while we carry out endto-end joint learning corresponding to a JSCC approach.…”

Section: Introductionmentioning

confidence: 99%

“…The similarity between the communication systems and end-to-end learning motivates the use of autoencoder based neural network architectures, which simultaneously learn encoding and decoding [14,15]. Recently, it has been shown that end-to-end approaches can also be utilized for physical layer secrecy [16][17][18][19]. In a wiretap channel setting, these techniques exploit the physical characteristics of the legitimate receiver's channel over the eavesdropper's, and allow communication with secrecy guarantees.…”

Section: Introductionmentioning

confidence: 99%

Privacy-Aware Communication Over a Wiretap Channel with Generative Networks

Erdemir¹,

Dragotti²,

Gündüz³

2021

Preprint

Self Cite

View full text Add to dashboard Cite

We study privacy-aware communication over a wiretap channel using end-to-end learning. Alice wants to transmit a source signal to Bob over a binary symmetric channel, while passive eavesdropper Eve tries to infer some sensitive attribute of Alice's source based on its overheard signal. Since we usually do not have access to true distributions, we propose a data-driven approach using variational autoencoder (VAE)-based joint source channel coding (JSCC). We show through simulations with the colored MNIST dataset that our approach provides high reconstruction quality at the receiver while confusing the eavesdropper about the latent sensitive attribute, which consists of the color and thickness of the digits. Finally, we consider a parallel-channel scenario, and show that our approach arranges the information transmission such that the channels with higher noise levels at the eavesdropper carry the sensitive information, while the non-sensitive information is transmitted over more vulnerable channels.

show abstract

“…In the context of wireless communication, one can approximate the channel distribution by samples and use the generator as a piece within the NN encoderdecoder chain [9], [10]. This was recently utilized to enable a form of secure communication in [11]. ii) Mutual information estimators: A recent breakthrough has shown that mutual information can be approximated through sampling of the random variables with the help of NNs [12].…”

Section: Introductionmentioning

confidence: 99%

Reinforce Security: A Model-Free Approach Towards Secure Wiretap Coding

Fritschek¹,

Schaefer²,

Wunder³

2021

Preprint

View full text Add to dashboard Cite

The use of deep learning-based techniques for approximating secure encoding functions has attracted considerable interest in wireless communications due to impressive results obtained for general coding and decoding tasks for wireless communication systems. Of particular importance is the development of model-free techniques that work without knowledge about the underlying channel. Such techniques utilize for example generative adversarial networks to estimate and model the conditional channel distribution, mutual information estimation as a reward function, or reinforcement learning. In this paper, the approach of reinforcement learning is studied and, in particular, the policy gradient method for a model-free approach of neural network-based secure encoding is investigated. Previously developed techniques for enforcing a certain coset structure on the encoding process can be combined with recent reinforcement learning approaches. This new approach is evaluated by extensive simulations, and it is demonstrated that the resulting decoding performance of an eavesdropper is capped at a certain error level.

show abstract

Adversarial Networks for Secure Wireless Communications

Cited by 15 publications

References 16 publications

On Learning-Assisted Content-Based Secure Image Transmission for Delay-Aware Systems with Randomly-Distributed Eavesdroppers -- Extended Version

On Learning-Assisted Content-Based Secure Image Transmission for Delay-Aware Systems with Randomly-Distributed Eavesdroppers -- Extended Version

Privacy-Aware Communication Over a Wiretap Channel with Generative Networks

Reinforce Security: A Model-Free Approach Towards Secure Wiretap Coding

Contact Info

Product

Resources

About