Related papers: Byzantine Failures Harm the Generalization of Robu…
Federated learning systems are susceptible to adversarial attacks. To combat this, we introduce a novel aggregator based on Huber loss minimization, and provide a comprehensive theoretical analysis. Under independent and identically…
We consider the problem of Byzantine fault-tolerance in the peer-to-peer (P2P) distributed gradient-descent method -- a prominent algorithm for distributed optimization in a P2P system. In this problem, the system comprises of multiple…
Federated Learning (FL) is notorious for its vulnerability to Byzantine attacks. Most current Byzantine defenses share a common inductive bias: among all the gradients, the densely distributed ones are more likely to be honest. However,…
Federated Learning (FL) enables multiple parties to train machine learning models collaboratively without sharing the raw training data. However, the federated nature of FL enables malicious clients to influence a trained model by injecting…
This paper focuses on the problem of adversarial attacks from Byzantine machines in a Federated Learning setting where non-Byzantine machines can be partitioned into disjoint clusters. In this setting, non-Byzantine machines in the same…
Byzantine-robust distributed learning (BRDL), in which computing devices are likely to behave abnormally due to accidental failures or malicious attacks, has recently become a hot research topic. However, even in the independent and…
Decentralized Learning (DL) is a peer--to--peer learning approach that allows a group of users to jointly train a machine learning model. To ensure correctness, DL should be robust, i.e., Byzantine users must not be able to tamper with the…
Cassandra is one of the most widely used distributed data stores these days. Cassandra supports flexible consistency guarantees over a wide-column data access model and provides almost linear scale-out performance. This enables application…
Federated Learning (FL) has gained significant attention for its privacy-preserving capabilities, enabling distributed devices to collaboratively train a global model without sharing raw data. However, its distributed nature forces the…
Federated Learning (FL) faces two major issues: privacy leakage and poisoning attacks, which may seriously undermine the reliability and security of the system. Overcoming them simultaneously poses a great challenge. This is because privacy…
Data poisoning and backdoor attacks manipulate training data in order to cause models to fail during inference. A recent survey of industry practitioners found that data poisoning is the number one concern among threats ranging from model…
This paper considers the problem of Byzantine fault-tolerance in multi-agent decentralized optimization. In this problem, each agent has a local cost function. The goal of a decentralized optimization algorithm is to allow the agents to…
The problem of designing distributed optimization algorithms that are resilient to Byzantine adversaries has received significant attention. For the Byzantine-resilient distributed optimization problem, the goal is to (approximately)…
Deep image classification models trained on vast amounts of web-scraped data are susceptible to data poisoning - a mechanism for backdooring models. A small number of poisoned samples seen during training can severely undermine a model's…
The integration of edge computing in next-generation mobile networks is bringing low-latency and high-bandwidth ubiquitous connectivity to a myriad of cyber-physical systems. This will further boost the increasing intelligence that is being…
Distributed learning has emerged as a leading paradigm for training large machine learning models. However, in real-world scenarios, participants may be unreliable or malicious, posing a significant challenge to the integrity and accuracy…
Making learners robust to adversarial perturbation at test time (i.e., evasion attacks) or training time (i.e., poisoning attacks) has emerged as a challenging task. It is known that for some natural settings, sublinear perturbations in the…
Existing research on federated learning has been focused on the setting where learning is coordinated by a centralized entity. Yet the greatest potential of future collaborative intelligence would be unleashed in a more open and…
The privacy-preserving federated learning schemes based on the setting of two honest-but-curious and non-colluding servers offer promising solutions in terms of security and efficiency. However, our investigation reveals that these schemes…
Distributed Learning often suffers from Byzantine failures, and there have been a number of works studying the problem of distributed stochastic optimization under Byzantine failures, where only a portion of workers, instead of all the…