Related papers: Exploit Gradient Skewness to Circumvent Byzantine …
Inherent client drifts caused by data heterogeneity, as well as vulnerability to Byzantine attacks within the system, hinder effective model training and convergence in federated learning (FL). This paper presents two new frameworks, named…
We investigate the Byzantine attack problem within the context of model training in distributed learning systems. While ensuring the convergence of current model training processes, common solvers (e.g. SGD, Adam, RMSProp, etc.) can be…
In this work, we consider the resilience of distributed algorithms based on stochastic gradient descent (SGD) in distributed learning with potentially Byzantine attackers, who could send arbitrary information to the parameter server to…
Privacy-preserving federated learning allows multiple users to jointly train a model with coordination of a central server. The server only learns the final aggregation result, thus the users' (private) training data is not leaked from the…
Recent work has shown that gradient updates in federated learning (FL) can unintentionally reveal sensitive information about a client's local data. This risk becomes significantly greater when a malicious server manipulates the global…
Federated Learning (FL) framework brings privacy benefits to distributed learning systems by allowing multiple clients to participate in a learning task under the coordination of a central server without exchanging their private data.…
We study a recently proposed large-scale distributed learning paradigm, namely Federated Learning, where the worker machines are end users' own devices. Statistical and computational challenges arise in Federated Learning particularly in…
Federated learning (FL) is a promising privacy-preserving distributed machine learning methodology that allows multiple clients (i.e., workers) to collaboratively train statistical models without disclosing private training data. Due to the…
We consider a distributed reinforcement learning setting where multiple agents separately explore the environment and communicate their experiences through a central server. However, $\alpha$-fraction of agents are adversarial and can…
Federated learning has emerged as a popular paradigm for collaboratively training a model from data distributed among a set of clients. This learning setting presents, among others, two unique challenges: how to protect privacy of the…
Recent advances in large-scale distributed learning algorithms have enabled communication-efficient training via SignSGD. Unfortunately, a major issue continues to plague distributed learning: namely, Byzantine failures may incur serious…
Federated learning (FL), integrating group fairness mechanisms, allows multiple clients to collaboratively train a global model that makes unbiased decisions for different populations grouped by sensitive attributes (e.g., gender and race).…
Robustness to Byzantine attacks is a necessity for various distributed training scenarios. When the training reduces to the process of solving a minimization problem, Byzantine robustness is relatively well-understood. However, other…
The growth of data, the need for scalability and the complexity of models used in modern machine learning calls for distributed implementations. Yet, as of today, distributed machine learning frameworks have largely ignored the possibility…
Gradient inversion attack (or input recovery from gradient) is an emerging threat to the security and privacy preservation of Federated learning, whereby malicious eavesdroppers or participants in the protocol can recover (partially) the…
Training modern neural networks or models typically requires averaging over a sample of high-dimensional vectors. Poisoning attacks can skew or bias the average vectors used to train the model, forcing the model to learn specific patterns…
One popular group of defense techniques against adversarial attacks is based on injecting stochastic noise into the network. The main source of robustness of such stochastic defenses however is often due to the obfuscation of the gradients,…
Federated Learning (FL) allows multiple clients to collaboratively train a model without sharing their private data. However, FL is vulnerable to Byzantine attacks, where adversaries manipulate client models to compromise the federated…
We identify obfuscated gradients, a kind of gradient masking, as a phenomenon that leads to a false sense of security in defenses against adversarial examples. While defenses that cause obfuscated gradients appear to defeat iterative…
Recent literature has shown that the control of False Discovery Rate (FDR) for distributed detection in wireless sensor networks (WSNs) can provide substantial improvement in detection performance over conventional design methodologies. In…