arXiv research

Paper shows data poisoning and Byzantine attacks are equivalent, impacting federated learning security.

Paper develops a robust federated recommendation system against poisoning attacks.

New research shows Byzantine failures hurt generalization more than data poisoning in robust distributed learning.

Dynamic defense against Byzantine poisoning in federated learning.

New framework detects and removes malicious model updates in federated learning.

While machine learning is going through an era of celebrated success, concerns have been raised about the vulnerability of its backbone: stochastic gradient descent (SGD). Recent approaches have been proposed to ensure the robustness of distributed SGD against adversarial (Byzantine) workers sending poisoned gradients …

PRISM-FCP improves federated prediction robustness against Byzantine attacks.

Federated learning enables training collaborative machine learning models at scale with many participants whilst preserving the privacy of their datasets. Standard federated learning techniques are vulnerable to Byzantine failures, biased local datasets, and poisoning attacks. In this paper we introduce Adaptive Federa…

Paper tackles Byzantine attacks in Federated Learning by clustering and robustifying.

Paper addresses Byzantine attacks in decentralized optimization over networks.

Paper tackles Byzantine attacks in distributed learning with a new ADMM method.

Byrd-SAGA reduces variance to robustify SGD against Byzantine attacks.

DynBRO learns robustly from dynamic Byzantine workers.

Machine Learning (ML) solutions are nowadays distributed, according to the so-called server/worker architecture. One server holds the model parameters while several workers train the model. Clearly, such architecture is prone to various types of component failures, which can be all encompassed within the spectrum of a …

We propose three new robust aggregation rules for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilie…

We propose a novel robust aggregation rule for distributed synchronous Stochastic Gradient Descent~(SGD) under a general Byzantine failure model. The attackers can arbitrarily manipulate the data transferred between the servers and the workers in the parameter server~(PS) architecture. We prove the Byzantine resilience…

Machine Learning (ML) solutions are nowadays distributed and are prone to various types of component failures, which can be encompassed in so-called Byzantine behavior. This paper introduces LiuBei, a Byzantine-resilient ML algorithm that does not trust any individual component in the network (neither workers nor serve…

CyBeR-0 optimizes federated learning with Byzantine resilience and reduced communication costs.

Recently, new defense techniques have been developed to tolerate Byzantine failures for distributed machine learning. The Byzantine model captures workers that behave arbitrarily, including malicious and compromised workers. In this paper, we break two prevailing Byzantine-tolerant techniques. Specifically we show robu…

Paper develops Byzantine-resilient algorithms for decentralized learning.

Novel algorithm resists Byzantine attacks in federated learning for PCA and LRCS.

Distributed machine learning algorithms enable learning of models from datasets that are distributed over a network without gathering the data at a centralized location. While efficient distributed algorithms have been developed under the assumption of faultless networks, failures that can render these algorithms nonfu…

Asynchronous distributed machine learning solutions have proven very effective so far, but always assuming perfectly functioning workers. In practice, some of the workers can however exhibit Byzantine behavior, caused by hardware failures, software bugs, corrupt data, or even malicious attacks. We introduce \emph{Karda…

SignSGD improves distributed learning by tolerating faulty devices, including Byzantine adversaries.

New method improves model accuracy in Byzantine-robust distributed learning by optimizing batch size.

New algorithm improves decentralized learning in the presence of Byzantine faults.

New methods improve Byzantine robustness in distributed learning.

New attack strategy circumvents CC framework's defences in federated learning.

Paper improves statistical efficiency of median-of-means estimator for Byzantine robust distributed inference.

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 of arbitrary (i.e., Byzantine) failures. In this paper, we study the robustness …

Robust algorithm for distributed optimization resistant to Byzantine failures.

Two novel algorithms improve distributed machine learning in the presence of Byzantine adversaries.

Machine learning has begun to play a central role in many applications. A multitude of these applications typically also involve datasets that are distributed across multiple computing devices/machines due to either design constraints (e.g., multiagent systems) or computational/privacy reasons (e.g., learning on smartp…

COMRADE is a communication-efficient, Byzantine-resilient second-order optimization algorithm.

This paper extends Newton's method to distributed learning, avoiding saddle points and handling Byzantine workers.

New federated learning protocols resist Byzantine failures and offer privacy guarantees.

Paper tackles Byzantine resilience in distributed multi-task learning.

New bucketing scheme improves Byzantine robustness for heterogeneous data.

Paper addresses robust federated linear bandits against Byzantine attacks.

Paper addresses fault-tolerance in distributed machine learning with stochastic gradient descent.

A method to robustly federate learning with non-i.i.d. data and Byzantine workers.

Paper proves mathematically that poisoning datasets can be detected.

Secure federated learning framework resists adversarial users.

New method defends RL agents from poisoning attacks without MDP knowledge.

Efficient poisoning attack converges to any target classifier with provable convergence.

This paper evaluates targeted data poisoning attacks by focusing on the hardest samples, improving evaluation and defense strategies.

Linear models can be poisoned by shifting a fraction of one class's data, revealing scaling laws and weight alignment.

Unified benchmarks assess data poisoning and backdoor attacks.