Federated learning is increasingly popular as it enables multiple parties with limited datasets and resources to train a machine learning model collaboratively. However, similar to other collaborative systems, federated learning is vulnerable to free-riders — participants who benefit from the global model without contributing. Free-riders compromise the integrity of the learning process and slow down the convergence of the global model, resulting in increased costs for honest participants. To address this challenge, we propose FRIDA: f ree- ri der d etection using privacy a ttacks. Instead of focusing on implicit effects of free-riding, FRIDA utilizes membership and property inference attacks to directly infer evidence of genuine client training. Our extensive evaluation demonstrates that FRIDA is effective across a wide range of scenarios.

In this paper, we present the SECURED project11Funded in part by the European Union (EU), Grant Agreement no. 10109571. Views and opinions expressed are those of the authors and do not necessarily reflect those of the EU or the Health and Digital Executive Agency. Neither the EU nor the granting authority are responsible for them., aimed at improving privacy-preserving processing of data in the health domain. The technologies developed in the project will be demonstrated in four health-related use cases and with the involvement of SME's selected through an open funding call.

Internet voting systems are supposed to meet the same high standards as traditional paper-based systems when used in real political elections: freedom of choice, universal and equal suffrage, secrecy of the ballot, and independent verifiability of the election result. Although numerous Internet voting systems have been proposed to achieve these challenging goals simultaneously, few come close in reality. We propose a novel publicly verifiable and practically efficient Internet voting system, DeVoS, that advances the state of the art. The main feature of DeVoS is its ability to protect voters' freedom of choice in several dimensions. First, voters in DeVoS can intuitively update their votes in a way that is deniable to observers but verifiable by the voters; in this way voters can secretly overwrite potentially coerced votes. Second, in addition to (basic) vote privacy, DeVoS also guarantees strong participation privacy by end-to-end hiding which voters have submitted ballots and which have not. Finally, DeVoS is fully compatible with Perfectly Private Audit Trail, a state-of-the-art Internet voting protocol with practical everlasting privacy. In combination, DeVoS offers a new way to secure free Internet elections with strong and long-term privacy properties.

To apply federated learning to drug discovery we developed a novel platform in the context of European Innovative Medicines Initiative (IMI) project MELLODDY (grant n°831472), which was comprised of 10 pharmaceutical companies, academic research labs, large industrial companies and startups. The MELLODDY platform was the first industry-scale platform to enable the creation of a global federated model for drug discovery without sharing the confidential data sets of the individual partners. The federated model was trained on the platform by aggregating the gradients of all contributing partners in a cryptographic, secure way following each training iteration. The platform was deployed on an Amazon Web Services (AWS) multi-account architecture running Kubernetes clusters in private subnets. Organisationally, the roles of the different partners were codified as different rights and permissions on the platform and administrated in a decentralized way. The MELLODDY platform generated new scientific discoveries which are described in a companion paper.

Federated learning algorithms are developed both for efficiency reasons and to ensure the privacy and confidentiality of personal and business data, respectively. Despite no data being shared explicitly, recent studies showed that the mechanism could still leak sensitive information. Hence, secure aggregation is utilized in many real-world scenarios to prevent attribution to specific participants. In this paper, we focus on the quality (i.e., the ratio of correct labels) of individual training datasets and show that such quality information could be inferred and attributed to specific participants even when secure aggregation is applied. Specifically, through a series of image recognition experiments, we infer the relative quality ordering of participants. Moreover, we apply the inferred quality information to stabilize training performance, measure the individual contribution of participants, and detect misbehavior.

Copyright © 2021 by SCITEPRESS – Science and Technology Publications, Lda. All rights reservedMachine learning models’ goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task. Property Inference Attacks exploit this and aim to infer from a given model (i.e., the target model) properties about the training dataset seemingly unrelated to the model’s primary goal. If the training data is sensitive, such an attack could lead to privacy leakage. In this paper, we investigate the influence of the target model’s complexity on the accuracy of this type of attack, focusing on convolutional neural network classifiers. We perform attacks on models that are trained on facial images to predict whether someone’s mouth is open. Our attacks’ goal is to infer whether the training dataset is balanced gender-wise. Our findings reveal that the risk of a privacy breach is present independently of the target model’s complexity: for all studied architectures, the attack’s accuracy is clearly over the baseline.

Abstract Shortly after it was first introduced in 2006,differential privacybecame the flagship data privacy definition. Since then, numerous variants and extensions were proposed to adapt it to different scenarios and attacker models. In this work, we propose a systematic taxonomy of these variants and extensions. We list all data privacy definitions based on differential privacy, and partition them into seven categories, depending on which aspect of the original definition is modified. These categories act like dimensions: variants from the same category cannot be combined, but variants from different categories can be combined to form new definitions. We also establish a partial ordering of relative strength between these notions by summarizing existing results. Furthermore, we list which of these definitions satisfy some desirable properties, like composition, postprocessing, and convexity by either providing a novel proof or collecting existing ones.

Abstract Machine learning algorithms have reached mainstream status and are widely deployed in many applications. The accuracy of such algorithms depends significantly on the size of the underlying training dataset; in reality a small or medium sized organization often does not have the necessary data to train a reasonably accurate model. For such organizations, a realistic solution is to train their machine learning models based on their joint dataset (which is a union of the individual ones). Unfortunately, privacy concerns prevent them from straightforwardly doing so. While a number of privacy-preserving solutions exist for collaborating organizations to securely aggregate the parameters in the process of training the models, we are not aware of any work that provides a rational framework for the participants to precisely balance the privacy loss and accuracy gain in their collaboration. In this paper, by focusing on a two-player setting, we model the collaborative training process as a two-player game where each player aims to achieve higher accuracy while preserving the privacy of its own dataset. We introduce the notion of Price of Privacy, a novel approach for measuring the impact of privacy protection on the accuracy in the proposed framework. Furthermore, we develop a game-theoretical model for different player types, and then either find or prove the existence of a Nash Equilibrium with regard to the strength of privacy protection for each player. Using recommendation systems as our main use case, we demonstrate how two players can make practical use of the proposed theoretical framework, including setting up the parameters and approximating the non-trivial Nash Equilibrium.

Machine learning algorithms have reached mainstream status and are widely deployed in many applications. The accuracy of such algorithms depends significantly on the size of the underlying training dataset; in reality a small or medium sized organization often does not have enough data to train a reasonably accurate model. For such organizations, a realistic solution is to train machine learning models based on a joint dataset (which is a union of the individual ones). Unfortunately, privacy concerns prevent them from straightforwardly doing so. While a number of privacy-preserving solutions exist for collaborating organizations to securely aggregate the parameters in the process of training the models, we are not aware of any work that provides a rational framework for the participants to precisely balance the privacy loss and accuracy gain in their collaboration. In this paper, we model the collaborative training process as a two-player game where each player aims to achieve higher accuracy while preserving the privacy of its own dataset. We introduce the notion of Price of Privacy, a novel approach for measuring the impact of privacy protection on the accuracy in the proposed framework. Furthermore, we develop a game-theoretical model for different player types, and then either find or prove the existence of a Nash Equilibrium with regard to the strength of privacy protection for each player.

In the cloud computing era, in order to avoid the computational burdens, many recommendation service providers tend to outsource their collaborative filtering computations to third-party cloud servers. In order to protect service quality, the integrity of computation results needs to be guaranteed. In this paper, we analyze two integrity verification approaches by Vaidya et al. and demonstrate their performances. In particular, we analyze the verification via auxiliary data approach which is only briefly mentioned in the original paper, and demonstrate the experimental results. We then propose a new solution to outsource all computations of the weighted Slope One algorithm in two-server setting and provide experimental results.