Privacy-Preserving Classification with Secret Vector Machines

Hartmann, Valentin; Modi, Konark; Pujol, Josep M.; West, Robert

doi:10.1145/3340531.3412051

Cited by 14 publications

(5 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As briefly discussed in Section 1, privacy violations for SVMs have been extensively studied (Farokhi, 2021; Hartmann et al, 2020; Li et al, 2014; Lin & Chen, 2008, 2011; Rubinstein et al, 2012; Vaidya et al, 2007; Zhang et al, 2019). The decision function released by an SVM, given by Equation (2), relies on evaluating the kernel function at the test point and the support vectors from the training data.…”

Section: Private Outcome‐weighted Learningmentioning

confidence: 99%

Differentially private outcome‐weighted learning for optimal dynamic treatment regime estimation

Spicker,

Moodie,

Shortreed

2024

Stat

View full text Add to dashboard Cite

Precision medicine is a framework for developing evidence‐based medical recommendations that seeks to determine the optimal sequence of treatments, tailored to all of the relevant, observable patient‐level characteristics. Because precision medicine relies on highly sensitive, patient‐level data, ensuring the privacy of participants is of great importance. Dynamic treatment regimes (DTRs) provide one formalization of precision medicine in a longitudinal setting. Outcome‐weighted learning (OWL) is a family of techniques for estimating optimal DTRs based on observational data. OWL techniques leverage support vector machine (SVM) classifiers in order to perform estimation. SVMs perform classification based on a set of influential points in the data known as support vectors. The classification rule produced by SVMs often requires direct access to the support vectors. Thus, releasing a treatment policy estimated with OWL requires the release of patient data for a subset of patients in the sample. As a result, the classification rules from SVMs constitute a severe privacy violation for those individuals whose data comprise the support vectors. This privacy violation is a major concern, particularly in light of the potentially highly sensitive medical data that are used in DTR estimation. Differential privacy has emerged as a mathematical framework for ensuring the privacy of individual‐level data, with provable guarantees on the likelihood that individual characteristics can be determined by an adversary. We provide the first investigation of differential privacy in the context of DTRs and provide a differentially private OWL estimator, with theoretical results allowing us to quantify the cost of privacy in terms of the accuracy of the private estimators.

show abstract

Section: Private Outcome‐weighted Learningmentioning

confidence: 99%

Differentially private outcome‐weighted learning for optimal dynamic treatment regime estimation

Spicker,

Moodie,

Shortreed

2024

Stat

View full text Add to dashboard Cite

show abstract

“…Traditional machine learning methods such as linear models (LM), decision trees (DT), and support vector machine models (SVM) have been applied to FL. Various approaches, including federated linear algorithms [14], federated tree models [15], [16], and federated support vector machines [17], have been proposed. As FL gained attention in research, scholars integrated expertise from the Internet of Things (IoT) and foundational mathematics to enhance and refine the basic framework.…”

Section: Related Work a The Development And Application Of Federated ...mentioning

confidence: 99%

FedDBO: A Novel Federated Learning Approach for Communication Cost and Data Heterogeneity Using Dung Beetle Optimizer

Wang,

Chen,

et al. 2024

IEEE Access

View full text Add to dashboard Cite

As an emerging distributed machine learning technology, federated learning has gained widespread attention due to its critical privacy protection mechanism. However, it also faces challenges such as high communication costs and heterogeneous client data.In order to address the above issues. This paper proposes a federated learning approach based on the dung beetle optimizer, named FedDBO. In this method, the model parameters uploaded from clients to the server are transformed into model scores. In each round of training, only some of the clients with high model scores need to be selected to upload their parameters to the server, thus reducing communication costs; Simultaneously, a model retraining strategy is introduced. After aggregating the model parameters sent by clients, the server performs a second iterative training on the aggregated model using its own metadata, thereby reducing data heterogeneity and improving model performance. In addition, a proof of convergence is provided, demonstrating that the model aggregated by FedDBO converges to the aggregated model of FedAvg after each training round. Finally, experiments indicate that when simulating various data heterogeneous environments on datasets, FedDBO exhibits higher accuracy and better stability compared to three other algorithms: FedAvg, FedShare, and FedPSO.

show abstract

“…Since its introduction, the concept of federated learning has rapidly become a research hotspot in the field of distributed machine learning, and many scholars have completed the implementation of classical machine learning models in the federated learning framework, such as the federated logistic regression proposed by Yang et al [6], the federated forest proposed by Lin et al [7] and the federated SVM proposed by Hartmann et al [8], and similarly, there are scholars have studied the implementation of deep learning models in a federal learning framework, such as Zhu X H et al on the application of CNN in a federal learning framework [9] and FedProx [10] , a new federal learning framework proposed by Sahu A K et al by training LSTM in a federal dataset and thus.…”

Section: Related Workmentioning

confidence: 99%

Adaptive federated learning aggregation strategies based on mobile edge computing

Liu

2023

Third International Conference on Machine Learning and Computer Application (ICMLCA 2022)

View full text Add to dashboard Cite

Privacy-Preserving Classification with Secret Vector Machines

Cited by 14 publications

References 15 publications

Differentially private outcome‐weighted learning for optimal dynamic treatment regime estimation

Differentially private outcome‐weighted learning for optimal dynamic treatment regime estimation

FedDBO: A Novel Federated Learning Approach for Communication Cost and Data Heterogeneity Using Dung Beetle Optimizer

Adaptive federated learning aggregation strategies based on mobile edge computing

Contact Info

Product

Resources

About