Related papers: Weight for Robustness: A Comprehensive Approach to…
Communication between workers and the master node to collect local stochastic gradients is a key bottleneck in a large-scale federated learning system. Various recent works have proposed to compress the local stochastic gradients to…
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 analyze the impact of transient and Byzantine faults on the construction of a maximal independent set in a general network. We adapt the self-stabilizing algorithm presented by Turau `for computing such a vertex set. Our algorithm is…
The alternating direction of multipliers method (ADMM) is a popular method to solve distributed consensus optimization utilizing efficient communication among various nodes in the network. However, in the presence of faulty or attacked…
Federated Learning (FL) enables heterogeneous clients to collaboratively train a shared model without centralizing their raw data, offering an inherent level of privacy. However, gradients and model updates can still leak sensitive…
Today's hardware technology presents a new challenge in designing robust systems. Deep submicron VLSI technology introduced transient and permanent faults that were never considered in low-level system designs in the past. Still, robustness…
Federated Learning (FL) paradigms enable large numbers of clients to collaboratively train Machine Learning models on private data. However, due to their multi-party nature, traditional FL schemes are left vulnerable to Byzantine attacks…
Recent advancements in machine learning have improved performance while also increasing computational demands. While federated and distributed setups address these issues, their structures remain vulnerable to malicious influences. In this…
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…
Privacy and Byzantine resilience (BR) are two crucial requirements of modern-day distributed machine learning. The two concepts have been extensively studied individually but the question of how to combine them effectively remains…
The ``Pulse Synchronization'' problem can be loosely described as targeting to invoke a recurring distributed event as simultaneously as possible at the different nodes and with a frequency that is as regular as possible. This target…
State-of-the-art asynchronous Byzantine fault-tolerant (BFT) protocols, such as HoneyBadgerBFT, BEAT, and Dumbo, have shown a performance comparable to partially synchronous BFT protocols. This paper studies two practical directions in…
This paper explores an old problem, {\em Byzantine fault-tolerant Broadcast} (BB), under a new model, {\em selective broadcast model}. The new model "interpolates" between the two traditional models in the literature. In particular, it…
This paper introduces a deterministic Byzantine consensus algorithm that relies on a new weak coordinator. As opposed to previous algorithms that cannot terminate in the presence of a faulty or slow coordinator, our algorithm can terminate…
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,…
This paper addresses federated learning (FL) in the context of malicious Byzantine attacks and data heterogeneity. We introduce a novel Robust Average Gradient Algorithm (RAGA), which uses the geometric median for aggregation and {allows…
In this paper, we investigate the problem of distributed learning (DL) in the presence of Byzantine attacks. For this problem, various robust bounded aggregation (RBA) rules have been proposed at the central server to mitigate the impact of…
Self-stabilization is a versatile approach to fault-tolerance since it permits a distributed system to recover from any transient fault that arbitrarily corrupts the contents of all memories in the system. Byzantine tolerance is an…
Distributed learning has become a promising computational parallelism paradigm that enables a wide scope of intelligent applications from the Internet of Things (IoT) to autonomous driving and the healthcare industry. This paper studies…
Given a set of robots with arbitrary initial location and no agreement on a global coordinate system, convergence requires that all robots asymptotically approach the exact same, but unknown beforehand, location. Robots are oblivious-- they…