Related papers: Analytical Study of Adversarial Strategies in Clus…
We investigate the maintenance of overlay networks under massive churn, i.e. nodes joining and leaving the network. We assume an adversary that may churn a constant fraction $\alpha n$ of nodes over the course of $\mathcal{O}(\log n)$…
Deep learning systems have become ubiquitous in many aspects of our lives. Unfortunately, it has been shown that such systems are vulnerable to adversarial attacks, making them prone to potential unlawful uses. Designing deep neural…
Consider a system in which players at nodes of an underlying graph G repeatedly play Prisoner's Dilemma against their neighbors. The players adapt their strategies based on the past behavior of their opponents by applying the so-called…
Network coding increases throughput and is robust against failures and erasures. However, since it allows mixing of information within the network, a single corrupted packet generated by a Byzantine attacker can easily contaminate the…
Recent years have seen significant interest in designing networks that are self-healing in the sense that they can automatically recover from adversarial attacks. Previous work shows that it is possible for a network to automatically…
The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks. However, despite the proliferation of such methods, there is currently no…
Byzantine agreement is a fundamental problem in fault-tolerant distributed computing that has been studied intensively for the last four decades. Much of the research has focused on a static Byzantine adversary, where the adversary is…
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 \cite{turau2007linear} for computing such a vertex…
Random linear network coding can be used in peer-to-peer networks to increase the efficiency of content distribution and distributed storage. However, these systems are particularly susceptible to Byzantine attacks. We quantify the impact…
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…
A major limitation of open P2P networks is the lack of strong identities. This allows any agent to attack the system by creating multiple false personas, thereby disrupting the overlay network's connectivity and sabotaging its operation. In…
A plethora of modern machine learning tasks require the utilization of large-scale distributed clusters as a critical component of the training pipeline. However, abnormal Byzantine behavior of the worker nodes can derail the training and…
Training of large scale models on distributed clusters is a critical component of the machine learning pipeline. However, this training can easily be made to fail if some workers behave in an adversarial (Byzantine) fashion whereby they…
In a recent paper, Jaggi et al. (INFOCOM 2007), presented a distributed polynomial-time rate-optimal network-coding scheme that works in the presence of Byzantine faults. We revisit their adversarial models and augment them with three,…
Nowadays more and more data are gathered for detecting and preventing cyber attacks. In cyber security applications, data analytics techniques have to deal with active adversaries that try to deceive the data analytics models and avoid…
In this paper, we propose a zeroth-order resilient distributed online algorithm for networks under Byzantine edge attacks. We assume that both the edges attacked by Byzantine adversaries and the objective function are time-varying.…
We study the problem of maintaining robust and sparse overlay networks in fully distributed settings where nodes continuously join and leave the system. This scenario closely models real-world unstructured peer-to-peer networks, where…
This study examines the application of adversarial attack concepts to control the evolution of cooperation in the prisoner's dilemma game in complex networks. Specifically, it proposes a simple adversarial attack method that drives players'…
Often an attacker tries to disconnect a network by destroying nodes or edges, while the defender counters using various resilience mechanisms. Examples include a music industry body attempting to close down a peer-to-peer file-sharing…
Deep neural networks (DNNs) are vulnerable to backdoor attack, which does not affect the network's performance on clean data but would manipulate the network behavior once a trigger pattern is added. Existing defense methods have greatly…