Generative Adversarial Networks (GANs) are increasingly adopted by the industry to synthesize realistic images using competing generator and discriminator neural networks. Due to data not being centrally available, Multi-Discriminator (MD)-GANs training frameworks employ multiple discriminators that have direct access to the real data. Distributedly training a joint GAN model entails the risk of free-riders, i.e., participants that aim to benefit from the common model while only pretending to participate in the training process. In this paper, we first define a free-rider as a participant without training data and then identify three possible actions: not training, training on synthetic data, or using pre-trained models for similar but not identical tasks that are publicly available. We conduct experiments to explore the impact of these three types of free-riders on the ability of MD-GANs to produce images that are indistinguishable from real data. We consequently design a defense against free-riders, termed DFG, which compares the performance of client discriminators to reference discriminators at the server. The defense allows the server to evict clients whose behavior does not match that of a benign client. The result shows that even when 67% of the clients are free-riders, the proposed DFG can improve synthetic image quality by up to 70.96%, compared to the case of no defense.

@en

Federated learning is a private-by-design distributed learning paradigm where clients train local models on their own data before a central server aggregates their local updates to compute a global model. Depending on the aggregation method used, the local updates are either the gradients or the weights of local learning models, e.g., FedAvg aggregates model weights. Unfortunately, recent reconstruction attacks apply a gradient inversion optimization on the gradient update of a single mini- batch to reconstruct the private data used by clients during training. As the state-of-the-art reconstruction attacks solely focus on single update, realistic adversarial scenarios are over- looked, such as observation across multiple updates and updates trained from multiple mini-batches. A few studies consider a more challenging adversarial scenario where only model updates based on multiple mini-batches are observable, and resort to computationally expensive simulation to untangle the underlying samples for each local step. In this paper, we propose AGIC, a novel Approximate Gradient Inversion Attack that efficiently and effectively reconstructs images from both model or gradient updates, and across multiple epochs. In a nutshell, AGIC (i) approximates gradient updates of used training samples from model updates to avoid costly simulation procedures, (ii) leverages gradient/model updates collected from multiple epochs, and (iii) assigns increasing weights to layers with respect to the neural network structure for reconstruction quality. We extensively evaluate AGIC on three datasets, namely CIFAR-10, CIFAR- 100 and ImageNet. Our results show that AGIC increases the peak signal-to-noise ratio (PSNR) by up to 50% compared to two representative state-of-the-art gradient inversion attacks. Furthermore, AGIC is faster than the state-of-the-art simulation- based attack, e.g., it is 5x faster when attacking FedAvg with 8 local steps in between model updates. @en

Federated learning (FL) enables collaborative learning between parties, called clients, without sharing the original and potentially sensitive data. To ensure fast convergence in the presence of such heterogeneous clients, it is imperative to timely select clients who can effectively contribute to learning. A realistic but overlooked case of heterogeneous clients are Mavericks, who monopolize the possession of certain data types, e.g., children hospitals possess most of the data on pediatric cardiology. In this paper, we address the importance and tackle the challenges of Mavericks by exploring two types of client selection strategies. First, we show theoretically and through simulations that the common contribution-based approach, Shapley Value, underestimates the contribution of Mavericks and is hence not effective as a measure to select clients. Then, we propose FedEMD, an adaptive strategy with competitive overhead based on the Wasserstein distance, supported by a proven convergence bound. As FedEMD adapts the selection probability such that Mavericks are preferably selected when the model benefits from improvement on rare classes, it consistently ensures the fast convergence in the presence of different types of Mavericks. Compared to existing strategies, including Shapley Value-based ones, FedEMD improves the convergence speed of neural network classifiers with FedAvg aggregation by 26.9% and its performance is consistent across various levels of heterogeneity.

@en

Attacks on Federated Learning (FL) can severely reduce the quality of the generated models and limit the usefulness of this emerging learning paradigm that enables on-premise decentralized learning. However, existing untargeted attacks are not practical for many scenarios as they assume that i) the attacker knows every update of benign clients, or ii) the attacker has a large dataset to locally train updates imitating benign parties. In this paper, we propose a data-free untargeted attack (DFA) that synthesizes malicious data to craft adversarial models without eavesdropping on the transmission of benign clients at all or requiring a large quantity of task-specific training data. We design two variants of DFA, namely DFA-R and DFA-G, which differ in how they trade off stealthiness and effectiveness. Specifically, DFA-R iteratively optimizes a malicious data layer to minimize the prediction confidence of all outputs of the global model, whereas DFA-G interactively trains a malicious data generator network by steering the output of the global model toward a particular class. Experimental results on Fashion-MNIST, Cifar-10, and SVHN show that DFA, despite requiring fewer assumptions than existing attacks, achieves similar or even higher attack success rate than state-of-the-art untargeted attacks against various state-of-the-art defense mechanisms. Concretely, they can evade all considered defense mechanisms in at least 50% of the cases for CIFAR-10 and often reduce the accuracy by more than a factor of 2. Consequently, we design REFD, a defense specifically crafted to protect against data-free attacks. REFD leverages a reference dataset to detect updates that are biased or have a low confidence. It greatly improves upon existing defenses by filtering out the malicious updates and achieves high global model accuracy.

@en

Federated Learning is an emerging distributed collaborative learning paradigm adopted by many of today's applications, e.g., keyboard prediction and object recognition. Its core principle is to learn from large amount of users data while preserving data privacy by design as collaborative users only need to share the machine learning models and keep data locally. The main challenge for such systems is to provide incentives to users to contribute high-quality models trained from their local data. In this paper, we aim to answer how well incentives recognize (in)accurate local models from honest and malicious users, and perceive their impacts on the model accuracy of federated learning systems. We first present a thorough survey on two contrasting perspectives: incentive mechanisms to measure the contribution of local models by honest users, and malicious users to deliberately degrade the overall model. We conduct simulation experiments to empirically demonstrate if existing contribution measurement schemes can disclose low-quality models from malicious users. Our results show there exists a clear tradeoff among measurement schemes in terms of the computational efficiency and effectiveness to distill the impact of malicious participants. We conclude this paper by discussing the research directions to design resilient contribution incentives.

@en