arXiv subjects

Mehdi Letafati

Publications and source records attributed to Mehdi Letafati.

13 recordsLinked to original sources

arXiv2025

Conditional Denoising Diffusion Autoencoders for Wireless Semantic Communications

Semantic communication (SemCom) systems aim to learn the mapping from low-dimensional semantics to high-dimensional ground-truth. While this is more akin to a "domain translation" problem, existing frameworks typically emphasize on channel-adaptive neural encoding-decoding schemes, lacking full exploration of signal distribution. Moreover, such methods so far have employed autoencoder-based architectures, where the encoding is tightly coupled to a matched decoder, causing scalability issues in practice. To address these gaps, diffusion autoencoder models are proposed for wireless SemCom. The goal is to learn a "semantic-to-clean" mapping, from the semantic space to the ground-truth probability distribution. A neural encoder at semantic transmitter extracts the high-level semantics, and a conditional diffusion model (CDiff) at the semantic receiver exploits the source distribution for signal-space denoising, while the received semantic latents are incorporated as the conditioning input to "steer" the decoding process towards the semantics intended by the transmitter. It is analytically proved that the proposed decoder model is a consistent estimator of the ground-truth data. Furthermore, extensive simulations over CIFAR-10 and MNIST datasets are provided along with design insights, highlighting the performance compared to legacy autoencoders and variational autoencoders (VAE). Simulations are further extended to the multi-user SemCom, identifying the dominating factors in a more realistic setup.

cs.LG↗

arXiv2024

Deep Joint Source Channel Coding for Privacy-Aware End-to-End Image Transmission

Deep neural network (DNN)-based joint source and channel coding is proposed for privacy-aware end-to-end image transmission against multiple eavesdroppers. Both scenarios of colluding and non-colluding eavesdroppers are considered. Unlike prior works that assume perfectly known and independent identically distributed (i.i.d.) source and channel statistics, the proposed scheme operates under unknown and non-i.i.d. conditions, making it more applicable to real-world scenarios. The goal is to transmit images with minimum distortion, while simultaneously preventing eavesdroppers from inferring certain private attributes of images. Simultaneously generalizing the ideas of privacy funnel and wiretap coding, a multi-objective optimization framework is expressed that characterizes the tradeoff between image reconstruction quality and information leakage to eavesdroppers, taking into account the structural similarity index (SSIM) for improving the perceptual quality of image reconstruction. Extensive experiments on the CIFAR-10 and CelebA, along with ablation studies, demonstrate significant performance improvements in terms of SSIM, adversarial accuracy, and the mutual information leakage compared to benchmarks. Experiments show that the proposed scheme restrains the adversarially-trained eavesdroppers from intercepting privatized data for both cases of eavesdropping a common secret, as well as the case in which eavesdroppers are interested in different secrets. Furthermore, useful insights on the privacy-utility trade-off are also provided.

cs.IT↗

arXiv2023

Generative AI-Based Probabilistic Constellation Shaping With Diffusion Models

Diffusion models are at the vanguard of generative AI research with renowned solutions such as ImageGen by Google Brain and DALL.E 3 by OpenAI. Nevertheless, the potential merits of diffusion models for communication engineering applications are not fully understood yet. In this paper, we aim to unleash the power of generative AI for PHY design of constellation symbols in communication systems. Although the geometry of constellations is predetermined according to networking standards, e.g., quadrature amplitude modulation (QAM), probabilistic shaping can design the probability of occurrence (generation) of constellation symbols. This can help improve the information rate and decoding performance of communication systems. We exploit the ``denoise-and-generate'' characteristics of denoising diffusion probabilistic models (DDPM) for probabilistic constellation shaping. The key idea is to learn generating constellation symbols out of noise, ``mimicking'' the way the receiver performs symbol reconstruction. This way, we make the constellation symbols sent by the transmitter, and what is inferred (reconstructed) at the receiver become as similar as possible, resulting in as few mismatches as possible. Our results show that the generative AI-based scheme outperforms deep neural network (DNN)-based benchmark and uniform shaping, while providing network resilience as well as robust out-of-distribution performance under low-SNR regimes and non-Gaussian assumptions. Numerical evaluations highlight 30% improvement in terms of cosine similarity and a threefold improvement in terms of mutual information compared to DNN-based approach for 64-QAM geometry.

cs.IT↗

arXiv2023

Conditional Denoising Diffusion Probabilistic Models for Data Reconstruction Enhancement in Wireless Communications

In this paper, conditional denoising diffusion probabilistic models (DDPMs) are proposed to enhance the data transmission and reconstruction over wireless channels. The underlying mechanism of DDPM is to decompose the data generation process over the so-called "denoising" steps. Inspired by this, the key idea is to leverage the generative prior of diffusion models in learning a "noisy-to-clean" transformation of the information signal to help enhance data reconstruction. The proposed scheme could be beneficial for communication scenarios in which a prior knowledge of the information content is available, e.g., in multimedia transmission. Hence, instead of employing complicated channel codes that reduce the information rate, one can exploit diffusion priors for reliable data reconstruction, especially under extreme channel conditions due to low signal-to-noise ratio (SNR), or hardware-impaired communications. The proposed DDPM-assisted receiver is tailored for the scenario of wireless image transmission using MNIST dataset. Our numerical results highlight the reconstruction performance of our scheme compared to the conventional digital communication, as well as the deep neural network (DNN)-based benchmark. It is also shown that more than 10 dB improvement in the reconstruction could be achieved in low SNR regimes, without the need to reduce the information rate for error correction.

cs.IT↗

arXiv2023

Diffusion Models for Wireless Communications

A comprehensive study on the applications of denoising diffusion models for wireless systems is provided. The article highlights the capabilities of diffusion models in learning complicated signal distributions, modeling wireless channels, and denoising and reconstructing distorted signals. First, fundamental working mechanism of diffusion models is introduced. Then the recent advances in applying diffusion models to wireless systems are reviewed. Next, two case studies are provided, where conditional diffusion models (CDiff) are proposed for data reconstruction enhancement, covering both the conventional digital communication systems, as well as the semantic communication (SemCom) setups. The first case study highlights about 10 dB improvement in data reconstruction under low-SNR regimes, while mitigating the need to transmit redundant bits for error correction codes in digital systems. The second study further extends the case to a SemCom setup, where diffusion autoencoders showcase superior performance compared to legacy autoencoders and variational autoencoder (VAE) architectures. Finally, future directions and existing challenges are discussed.

cs.IT↗

arXiv2023

Denoising Diffusion Probabilistic Models for Hardware-Impaired Communications

Generative AI has received significant attention among a spectrum of diverse industrial and academic domains, thanks to the magnificent results achieved from deep generative models such as generative pre-trained transformers (GPT) and diffusion models. In this paper, we explore the applications of denoising diffusion probabilistic models (DDPMs) in wireless communication systems under practical assumptions such as hardware impairments (HWI), low-SNR regime, and quantization error. Diffusion models are a new class of state-of-the-art generative models that have already showcased notable success with some of the popular examples by OpenAI1 and Google Brain2. The intuition behind DDPM is to decompose the data generation process over small ``denoising'' steps. Inspired by this, we propose using denoising diffusion model-based receiver for a practical wireless communication scheme, while providing network resilience in low-SNR regimes, non-Gaussian noise, different HWI levels, and quantization error. We evaluate the reconstruction performance of our scheme in terms of mean-squared error (MSE) metric. Our results show that more than 25 dB improvement in MSE is achieved compared to deep neural network (DNN)-based receivers. We also highlight robust out-of-distribution performance under non-Gaussian noise.

cs.IT↗

arXiv2023

Probabilistic Constellation Shaping With Denoising Diffusion Probabilistic Models: A Novel Approach

With the incredible results achieved from generative pre-trained transformers (GPT) and diffusion models, generative AI (GenAI) is envisioned to yield remarkable breakthroughs in various industrial and academic domains. In this paper, we utilize denoising diffusion probabilistic models (DDPM), as one of the state-of-the-art generative models, for probabilistic constellation shaping in wireless communications. While the geometry of constellations is predetermined by the networking standards, probabilistic constellation shaping can help enhance the information rate and communication performance by designing the probability of occurrence (generation) of constellation symbols. Unlike conventional methods that deal with an optimization problem over the discrete distribution of constellations, we take a radically different approach. Exploiting the ``denoise-and-generate'' characteristic of DDPMs, the key idea is to learn how to generate constellation symbols out of noise, ``mimicking'' the way the receiver performs symbol reconstruction. By doing so, we make the constellation symbols sent by the transmitter, and what is inferred (reconstructed) at the receiver become as similar as possible. Our simulations show that the proposed scheme outperforms deep neural network (DNN)-based benchmark and uniform shaping, while providing network resilience as well as robust out-of-distribution performance under low-SNR regimes and non-Gaussian noise. Notably, a threefold improvement in terms of mutual information is achieved compared to DNN-based approach for 64-QAM geometry.

cs.IT↗

arXiv2023

Secure Deep-JSCC Against Multiple Eavesdroppers

In this paper, a generalization of deep learning-aided joint source channel coding (Deep-JSCC) approach to secure communications is studied. We propose an end-to-end (E2E) learning-based approach for secure communication against multiple eavesdroppers over complex-valued fading channels. Both scenarios of colluding and non-colluding eavesdroppers are studied. For the colluding strategy, eavesdroppers share their logits to collaboratively infer private attributes based on ensemble learning method, while for the non-colluding setup they act alone. The goal is to prevent eavesdroppers from inferring private (sensitive) information about the transmitted images, while delivering the images to a legitimate receiver with minimum distortion. By generalizing the ideas of privacy funnel and wiretap channel coding, the trade-off between the image recovery at the legitimate node and the information leakage to the eavesdroppers is characterized. To solve this secrecy funnel framework, we implement deep neural networks (DNNs) to realize a data-driven secure communication scheme, without relying on a specific data distribution. Simulations over CIFAR-10 dataset verifies the secrecy-utility trade-off. Adversarial accuracy of eavesdroppers are also studied over Rayleigh fading, Nakagami-m, and AWGN channels to verify the generalization of the proposed scheme. Our experiments show that employing the proposed secure neural encoding can decrease the adversarial accuracy by 28%.

cs.IT↗

arXiv2023

Digital Healthcare in The Metaverse: Insights into Privacy and Security

In this article, we study the privacy and security aspects of the metaverse in the context of digital healthcare. Our studies include the security aspects of data collection and communications for access to the metaverse, the privacy and security threats of employing Machine Learning and Artificial Intelligence (AI/ML) algorithms for metaverse healthcare, and the privacy of social interactions among patients in the metaverse from a human-centric perspective. In this article, we aim to provide new perspectives and less-investigated solutions, which are shown to be promising mechanisms in the context of wireless communications and computer science and can be considered novel solutions to be applied to healthcare metaverse services. Topics include physical layer security (PHYSec), Semantic Metaverse Communications (SMC), Differential Privacy (DP), and Adversarial Machine Learning (AML). As a case study, we propose distributed differential privacy for the metaverse healthcare systems, where each virtual clinic perturbs its medical model vector to enhance privacy against malicious actors and curious servers. Through our experiments on the Breast Cancer Wisconsin Dataset (BCWD), we highlight the privacy-utility trade-off for different adjustable levels of privacy.

cs.CR↗

arXiv2023

Global Differential Privacy for Distributed Metaverse Healthcare Systems

Metaverse-enabled digital healthcare systems are expected to exploit an unprecedented amount of personal health data, while ensuring that sensitive or private information of individuals are not disclosed. Machine learning and artificial intelligence (ML/AI) techniques can be widely utilized in metaverse healthcare systems, such as virtual clinics and intelligent consultations. In such scenarios, the key challenge is that data privacy laws might not allow virtual clinics to share their medical data with other parties. Moreover, clinical AI/ML models themselves carry extensive information about the medical datasets, such that private attributes can be easily inferred by malicious actors in the metaverse (if not rigorously privatized). In this paper, inspired by the idea of "incognito mode", which has recently been developed as a promising solution to safeguard metaverse users' privacy, we propose global differential privacy for the distributed metaverse healthcare systems. In our scheme, a randomized mechanism in the format of artificial "mix-up" noise is applied to the federated clinical ML/AI models before sharing with other peers. This way, we provide an adjustable level of distributed privacy against both the malicious actors and honest-but curious metaverse servers. Our evaluations on breast cancer Wisconsin dataset (BCWD) highlight the privacy-utility trade-off (PUT) in terms of diagnosis accuracy and loss function for different levels of privacy. We also compare our private scheme with the non-private centralized setup in terms of diagnosis accuracy.

cs.CR↗

arXiv2023

Unlocking Metaverse-as-a-Service The three pillars to watch: Privacy and Security, Edge Computing, and Blockchain

In this article, the authors provide a comprehensive overview on three core pillars of metaverse-as-a-service (MaaS) platforms; privacy and security, edge computing, and blockchain technology. The article starts by investigating security aspects for the wireless access to the metaverse. Then it goes through the privacy and security issues inside the metaverse from data-centric, learning-centric, and human-centric points-of-view. The authors address private and secure mechanisms for privatizing sensitive data attributes and securing machine learning algorithms running in a distributed manner within the metaverse platforms. Novel visions and less-investigated methods are reviewed to help mobile network operators and metaverse service providers facilitate the realization of secure and private MaaS through different layers of the metaverse, ranging from the access layer to the social interactions among clients. Later in the article, it has been explained how the paradigm of edge computing can strengthen different aspects of the metaverse. Along with that, the challenges of using edge computing in the metaverse have been comprehensively investigated. Additionally, the paper has comprehensively investigated and analyzed 10 main challenges of MaaS platforms and thoroughly discussed how blockchain technology provides solutions for these constraints. At the final, future vision and directions, such as content-centric security and zero-trust metaverse, some blockchain's unsolved challenges are also discussed to bring further insights for the network designers in the metaverse era.

cs.CR↗

arXiv2022

Multi-Transmitter Coded Caching with Secure Delivery over Linear Networks -- Extended Version

In this paper, we consider multiple cache-enabled end-users connected to multiple transmitters through a linear network. We also prevent a totally passive eavesdropper, who sniffs the packets in the delivery phase, from obtaining any information about the original files in cache-aided networks. Three different secure centralized multi-transmitter coded caching scenarios namely, secure multi-transmitter coded caching, secure multi-transmitter coded caching with reduced subpacketization, and secure multi-transmitter coded caching with reduced feedback, are considered and closed-form coding delay and secret shared key storage expressions are provided. As our security guarantee, we show that the delivery phase does not reveal any information to the eavesdropper using the mutual information metric. Moreover, we investigate the secure decentralized multi-transmitter coded caching scenario, in which there is no cooperation between the clients and transmitters during the cache content placement phase and study its performance compared to the centralized scheme. We analyze the system's performance in terms of Coding Delay and guarantee the security of our presented schemes using the Mutual Information metric. Numerical evaluations verify that security incurs a negligible cost in terms of memory usage when the number of files and users are scaled up, in both centralized and decentralized scenarios. Also, we numerically show that by increasing the number of files and users, the secure coding delay of centralized and decentralized schemes became asymptotically equal.

cs.IT↗

arXiv2021

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

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 scheme outperforms the state-of-the-arts by achieving considerable gains in terms of security and the delay requirement.

cs.IT↗