Related papers: Byzantine-Tolerant Machine Learning
Stochastic Gradient Descent (SGD) is a fundamental algorithm in machine learning, representing the optimization backbone for training several classic models, from regression to neural networks. Given the recent practical focus on…
Ensuring that an AI system behaves reliably and as intended, especially in the presence of unexpected faults or adversarial conditions, is a complex challenge. Inspired by the field of Byzantine Fault Tolerance (BFT) from distributed…
The ability to perform repeated Byzantine agreement lies at the heart of important applications such as blockchain price oracles or replicated state machines. Any such protocol requires the following properties: (1) \textit{Byzantine…
We investigate robust federated learning, where a group of workers collaboratively train a shared model under the orchestration of a central server in the presence of Byzantine adversaries capable of arbitrary and potentially malicious…
Recently, there is a growing interest in the study of median-based algorithms for distributed non-convex optimization. Two prominent such algorithms include signSGD with majority vote, an effective approach for communication reduction via…
In this work, we formalize a novel shared memory model inspired by the popular GPU architecture. Within this model, we develop algorithmic solutions to the Byzantine Consensus problem and analyze their fault-resilience.
Federated learning is a distributed training framework vulnerable to Byzantine attacks, particularly when over 50% of clients are malicious or when datasets are highly non-independent and identically distributed (non-IID). Additionally,…
This paper considers the problem of Byzantine fault-tolerance in distributed multi-agent optimization. In this problem, each agent has a local cost function, and in the fault-free case, the goal is to design a distributed algorithm that…
Byzantine-Fault-Tolerant (BFT) systems are rapidly emerging as a viable technology for production-grade systems, notably in closed consortia deployments for nancial and supply-chain applications. Unfortunately, most algorithms proposed so…
Blockchain technology offers a decentralized and secure method for storing and authenticating data, rendering it well-suited for various applications such as digital currencies, supply chain management, and voting systems. However, the…
Jointly addressing Byzantine attacks and privacy leakage in distributed machine learning (DML) has become an important issue. A common strategy involves integrating Byzantine-resilient aggregation rules with differential privacy mechanisms.…
We study the Byzantine lattice agreement (BLA) problem in asynchronous distributed message passing systems. In the BLA problem, each process proposes a value from a join semi-lattice and needs to output a value also in the lattice such that…
Byzantine machine learning has garnered considerable attention in light of the unpredictable faults that can occur in large-scale distributed learning systems. The key to secure resilience against Byzantine machines in distributed learning…
We consider gradient coding in the presence of an adversary, controlling so-called malicious workers trying to corrupt the computations. Previous works propose the use of MDS codes to treat the inputs of the malicious workers as errors and…
\textit{Federated learning} (FL) is a nascent distributed learning paradigm to train a shared global model without violating users' privacy. FL has been shown to be vulnerable to various Byzantine attacks, where malicious participants could…
Replicated services are inherently vulnerable to failures and security breaches. In a long-running system, it is, therefore, indispensable to maintain a reconfiguration mechanism that would replace faulty replicas with correct ones. An…
Robust aggregation is the core operation in Byzantine-tolerant federated learning. To ensure the quality of aggregation independently of data distribution or attacks, validity conditions are needed. They provide geometric guarantees of…
Gradient-based training in federated learning is known to be vulnerable to faulty/malicious clients, which are often modeled as Byzantine clients. To this end, previous work either makes use of auxiliary data at parameter server to verify…
This paper aims to solve a distributed learning problem under Byzantine attacks. In the underlying distributed system, a number of unknown but malicious workers (termed as Byzantine workers) can send arbitrary messages to the master and…
The problem of distributed optimization requires a group of agents to reach agreement on a parameter that minimizes the average of their local cost functions using information received from their neighbors. While there are a variety of…