Related papers: Adversary-Augmented Simulation to evaluate fairnes…
This paper explores the vulnerability of machine learning models to simple single-feature adversarial attacks in the context of Ethereum fraudulent transaction detection. Through comprehensive experimentation, we investigate the impact of…
The vulnerability of machine learning models to adversarial attacks has been attracting considerable attention in recent years. Most existing studies focus on the behavior of stand-alone single-agent learners. In comparison, this work…
While blockchains initially gained popularity in the realm of cryptocurrencies, their widespread adoption is expanding beyond conventional applications, driven by the imperative need for enhanced data security. Despite providing a secure…
Adversarial examples, which are slightly perturbed inputs generated with the aim of fooling a neural network, are known to transfer between models; adversaries which are effective on one model will often fool another. This concept of…
Performance and scalability are major concerns for blockchains: permissionless systems are typically limited by slow proof of X consensus algorithms and sequential post-order transaction execution on every node of the network. By…
A new framework for a secure and robust consensus in blockchain-based IoT networks is proposed using machine learning. Hyperledger fabric, which is a blockchain platform developed as part of the Hyperledger project, though looks very apt…
We study a robust, i.e. in presence of malicious participants, multi-agent multi-armed bandit problem where multiple participants are distributed on a fully decentralized blockchain, with the possibility of some being malicious. The rewards…
Deep neural networks are known to be extremely vulnerable to adversarial examples under white-box setting. Moreover, the malicious adversaries crafted on the surrogate (source) model often exhibit black-box transferability on other models…
Trust models are essential components of networks of any nature, as they refer to confidence frameworks to evaluate and verify if their participants act reliably and fairly. They are necessary to any social, organizational, or computer…
Hyperledger Fabric is a popular open-source project for deploying permissioned blockchains. Many performance characteristics of the latest Hyperledger Fabric, such as performance characteristics of each phase, the impacts of ordering…
This work aims to provide a more secure access control in Hyperledger Fabric blockchain by combining multiple ID's, attributes, and policies with the components that regulate access control. The access control system currently used by…
Federated Learning presents a nascent approach to machine learning, enabling collaborative model training across decentralized devices while safeguarding data privacy. However, its distributed nature renders it susceptible to adversarial…
The rapid growth of blockchain systems leads to increasing interest in understanding and comparing blockchain performance at scale. In this paper, we focus on analyzing the performance of Hyperledger Fabric v1.1 - one of the most popular…
Blockchain applications may offer better fault-tolerance, integrity, traceability and transparency compared to centralized solutions. Despite these benefits, few businesses switch to blockchain-based applications. Industries worry that the…
Modern distributed data management systems face a new challenge: how can autonomous, mutually-distrusting parties cooperate safely and effectively? Addressing this challenge brings up questions familiar from classical distributed systems:…
Tendermint-core blockchains (e.g. Cosmos) are considered today one of the most viable alternatives for the highly energy consuming proof-of-work blockchains such as Bitcoin and Ethereum. Their particularity is that they aim at offering…
Blockchain-based Distributed Ledgers (DLs) promise to transform the existing financial system by making it truly democratic. In the past decade, blockchain technology has seen many novel applications ranging from the banking industry to…
In this paper we analyze Tendermint proposed in [7], one of the most popular blockchains based on PBFT Consensus. The current paper dissects Tendermint under various system communication models and Byzantine adversaries. Our methodology…
Object detection models are critical components of automated systems, such as autonomous vehicles and perception-based robots, but their sensitivity to adversarial attacks poses a serious security risk. Progress in defending these models…
Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an…