Secure Aggregation is Not Private Against Membership Inference Attacks

Secure aggregation (SecAgg) is a commonly-used privacy-enhancing mechanism in federated learning, affording the server access only to the aggregate of model updates while safeguarding the confidentiality of individual updates. Despite widespread claims regarding SecAgg's privacy-preserving capabilities, a formal analysis of its privacy is lacking, making such presumptions unjustified. In this paper, we delve into the privacy implications of SecAgg by treating it as a local differential privacy (LDP) mechanism for each local update. We design a simple attack wherein an adversarial server seeks to discern which update vector a client submitted, out of two possible ones, in a single training round of federated learning under SecAgg. By conducting privacy auditing, we assess the success probability of this attack and quantify the LDP guarantees provided by SecAgg. Our numerical results unveil that, contrary to prevailing claims, SecAgg offers weak privacy against membership inference attacks even in a single training round. Indeed, it is difficult to hide a local update by adding other independent local updates when the updates are of high dimension. Our findings underscore the imperative for additional privacy-enhancing mechanisms, such as noise injection, in federated learning.

FedStruct: Federated Decoupled Learning over Interconnected Graphs

We address the challenge of federated learning on graph-structured data distributed across multiple clients. Specifically, we focus on the prevalent scenario of interconnected subgraphs, where inter-connections between different clients play a critical role. We present a novel framework for this scenario, named FedStruct, that harnesses deep structural dependencies. To uphold privacy, unlike existing methods, FedStruct eliminates the necessity of sharing or generating sensitive node features or embeddings among clients. Instead, it leverages explicit global graph structure information to capture inter-node dependencies. We validate the effectiveness of FedStruct through experimental results conducted on six datasets for semi-supervised node classification, showcasing performance close to the centralized approach across various scenarios, including different data partitioning methods, varying levels of label availability, and number of clients.

Time vs. Frequency Domain DPD for Massive MIMO: Methods and Performance Analysis

The use of up to hundreds of antennas in massive multi-user (MU) multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM) poses a complexity challenge for digital predistortion (DPD) aiming to linearize the nonlinear power amplifiers (PAs). While the complexity for conventional time domain (TD) DPD scales with the number of PAs, frequency domain (FD) DPD has a complexity scaling with the number of user equipments (UEs). In this work, we provide a comprehensive analysis of different state-of-the-art TD and FD-DPD schemes in terms of complexity and linearization performance in both rich scattering and line-of-sight (LOS) channels. We also propose a novel low-complexity FD convolutional neural network (CNN) DPD. The analysis shows that FD-DPD, particularly the proposed FD CNN, is preferable in LOS scenarios with few users, due to the favorable trade-off between complexity and linearization performance. On the other hand, in scenarios with more users or isotropic scattering channels, significant intermodulation distortions among UEs degrade FD-DPD performance, making TD-DPD more suitable.

Blind Frequency-Domain Equalization Using Vector-Quantized Variational Autoencoders

We propose a novel frequency-domain blind equalization scheme for coherent optical communications. The method is shown to achieve similar performance to its recently proposed time-domain counterpart with lower computational complexity, while outperforming the commonly used CMA-based equalizers.

Impact of Phase Noise on Uplink Cell-Free Massive MIMO OFDM

Cell-Free massive MIMO networks provide huge power gains and resolve inter-cell interference by coherent processing over a massive number of distributed instead of co-located antennas in access points (APs). Cost-efficient hardware is preferred but imperfect local oscillators in both APs and users introduce multiplicative phase noise (PN), which affects the phase coherence between APs and users even with centralized processing. In this paper, we first formulate the system model of a PN-impaired uplink Cell-Free massive MIMO orthogonal frequency division multiplexing network, and then propose a PN-aware linear minimum mean square error channel estimator and derive a PN-impaired uplink spectral efficiency expression. Numerical results are used to quantify the spectral efficiency gain of the proposed channel estimator over alternative schemes for different receiving combiners.

Balancing Privacy and Security in Federated Learning with FedGT: A Group Testing Framework

We propose FedGT, a novel framework for identifying malicious clients in federated learning with secure aggregation. Inspired by group testing, the framework leverages overlapping groups of clients to detect the presence of malicious clients in the groups and to identify them via a decoding operation. The identified clients are then removed from the training of the model, which is performed over the remaining clients. FedGT strikes a balance between privacy and security, allowing for improved identification capabilities while still preserving data privacy. Specifically, the server learns the aggregated model of the clients in each group. The effectiveness of FedGT is demonstrated through extensive experiments on the MNIST and CIFAR-10 datasets, showing its ability to identify malicious clients with low misdetection and false alarm probabilities, resulting in high model utility.

Blind Channel Equalization Using Vector-Quantized Variational Autoencoders

State-of-the-art high-spectral-efficiency communication systems employ high-order modulation formats coupled with high symbol rates to accommodate the ever-growing demand for data rate-hungry applications. However, such systems are more vulnerable to linear and nonlinear transmission impairments, and it is important to mitigate the performance loss via digital signal processing. In this paper, we propose a novel machine learning approach for blind channel equalization and estimation using the vector quantized (VQ) \ac{VAE} framework. The proposed approach generalizes the applicability of the conventional \ac{VAE}-based equalizer to nonlinear systems employing high-order modulation formats by introducing a codebook component and an associated novel loss function. We evaluate the performance of the proposed method over a linear additive white Gaussian noise channel with intersymbol interference and two nonlinear scenarios. Simulation results show that the proposed method can achieve similar performance as a data aided equalizer using the \acf{MMSE} criterion, and outperforms the blind\ac{CMA} and the \ac{VAE}-based channel equalizer. Furthermore, we show that for the linear channel, the proposed scheme exhibits better convergence properties than the \ac{MMSE}-based, the \ac{CMA}-based, and the \ac{VAE}-based equalizers in terms of both convergence speed and robustness to variations in training batch size and learning rate.

Rateless Autoencoder Codes: Trading off Decoding Delay and Reliability

Most of today's communication systems are designed to target reliable message recovery after receiving the entire encoded message (codeword). However, in many practical scenarios, the transmission process may be interrupted before receiving the complete codeword. This paper proposes a novel rateless autoencoder (AE)-based code design suitable for decoding the transmitted message before the noisy codeword is fully received. Using particular dropout strategies applied during the training process, rateless AE codes allow to trade off between decoding delay and reliability, providing a graceful improvement of the latter with each additionally received codeword symbol. The proposed rateless AEs significantly outperform the conventional AE designs for scenarios where it is desirable to trade off reliability for lower decoding delay.

Frequency-domain digital predistortion for Massive MU-MIMO-OFDM Downlink

Digital predistortion (DPD) is a method commonly used to compensate for the nonlinear effects of power amplifiers (PAs). However, the computational complexity of most DPD algorithms becomes an issue in the downlink of massive multi-user (MU) multiple-input multiple-output (MIMO) orthogonal frequency division multiplexing (OFDM), where potentially up to several hundreds of PAs in the base station (BS) require linearization. In this paper, we propose a convolutional neural network (CNN)-based DPD in the frequency domain, taking place before the precoding, where the dimensionality of the signal space depends on the number of users, instead of the number of BS antennas. Simulation results on generalized memory polynomial (GMP)-based PAs show that the proposed CNN-based DPD can lead to very large complexity savings as the number of BS antenna increases at the expense of a small increase in power to achieve the same symbol error rate (SER).

Generalized Spatially-Coupled Parallel Concatenated Codes With Partial Repetition

A new class of spatially-coupled turbo-like codes (SC-TCs), dubbed generalized spatially coupled parallel concatenated codes (GSC-PCCs), is introduced. These codes are constructed by applying spatial coupling on parallel concatenated codes (PCCs) with a fraction of information bits repeated $q$ times. GSC-PCCs can be seen as a generalization of the original spatially-coupled parallel concatenated codes proposed by Moloudi et al. [2]. To characterize the asymptotic performance of GSC-PCCs, we derive the corresponding density evolution equations and compute their decoding thresholds. The threshold saturation effect is observed and proven. Most importantly, we rigorously prove that any rate-$R$ GSC-PCC ensemble with 2-state convolutional component codes achieves at least a fraction $1-\frac{R}{R+q}$ of the capacity of the binary erasure channel (BEC) for repetition factor $q\geq2$ and this multiplicative gap vanishes as $q$ tends to infinity. To the best of our knowledge, this is the first class of SC-TCs that are proven to be capacity-achieving. Further, the connection between the strength of the component codes, the decoding thresholds of GSC-PCCs, and the repetition factor are established. The superiority of the proposed codes with finite blocklength is exemplified by comparing their error performance with that of existing SC-TCs via computer simulations.