Related papers: Cooperating Attackers in Neural Cryptography

As collaborative learning allows joint training of a model using multiple sources of data, the security problem has been a central concern. Malicious users can upload poisoned data to prevent the model's convergence or inject hidden…

Recently we could see several institutions coming together to create consortium based blockchain networks such as Hyperledger. Although for applications of blockchain such as Bitcoin, Litcoin, etc. the majority-attack might not be a great…

Federated learning is a popular strategy for training models on distributed, sensitive data, while preserving data privacy. Prior work identified a range of security threats on federated learning protocols that poison the data or the model.…

Federated learning allows multiple participants to collaboratively train a central model without sharing their private data. However, this distributed nature also exposes new attack surfaces. In particular, backdoor attacks allow attackers…

Mixtures of classifiers (a.k.a. randomized ensembles) have been proposed as a way to improve robustness against adversarial attacks. However, it has been shown that existing attacks are not well suited for this kind of classifiers. In this…

Finite mixtures of classifiers (a.k.a. randomized ensembles) have been proposed as a way to improve robustness against adversarial attacks. However, existing attacks have been shown to not suit this kind of classifier. In this paper, we…

In neural network (NN) security, safeguarding model integrity and resilience against adversarial attacks has become paramount. This study investigates the application of stochastic computing (SC) as a novel mechanism to fortify NN models.…

NeuraCrypt (Yara et al. arXiv 2021) is an algorithm that converts a sensitive dataset to an encoded dataset so that (1) it is still possible to train machine learning models on the encoded data, but (2) an adversary who has access only to…

Graph Neural Networks (GNNs), specifically designed to process the graph data, have achieved remarkable success in various applications. Link stealing attacks on graph data pose a significant privacy threat, as attackers aim to extract…

Malicious server (MS) attacks have enabled the scaling of data stealing in federated learning to large batch sizes and secure aggregation, settings previously considered private. However, many concerns regarding the client-side…

The financial sector presents many opportunities to apply various machine learning techniques. Centralized machine learning creates a constraint which limits further applications in finance sectors. Data privacy is a fundamental challenge…

Recommendation and collaborative filtering systems are important in modern information and e-commerce applications. As these systems are becoming increasingly popular in the industry, their outputs could affect business decision making,…

The vulnerability of machine learning systems to adversarial attacks questions their usage in many applications. In this paper, we propose a randomized diversification as a defense strategy. We introduce a multi-channel architecture in a…

Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed…

Characterizing attacker behavior with respect to Cyber-Physical Systems is important to assuring the security posture and resilience of these systems. Classical cyber vulnerability assessment approaches rely on the knowledge and experience…

We ask whether neural networks can learn to use secret keys to protect information from other neural networks. Specifically, we focus on ensuring confidentiality properties in a multiagent system, and we specify those properties in terms of…

Federated learning enables thousands of participants to construct a deep learning model without sharing their private training data with each other. For example, multiple smartphones can jointly train a next-word predictor for keyboards…

The notion that collaborative machine learning can ensure privacy by just withholding the raw data is widely acknowledged to be flawed. Over the past seven years, the literature has revealed several privacy attacks that enable adversaries…

Growing interest in utilizing the wireless spectrum by heterogeneous devices compels us to rethink the physical layer security to protect the transmitted waveform from an eavesdropper. We propose an end-to-end symmetric key neural…

This paper aims to review the encountered technical contradictions when an attacker meets the cipher-images encrypted by the image encryption schemes (algorithms) proposed in 2018 from the viewpoint of an image cryptanalyst. The most…