Partitioning-Based Mechanisms Under Personalized Differential Privacy

Li, Haoran; Xiong, Li; Ji, Zhanglong; Jiang, Xiaoqian

doi:10.1007/978-3-319-57454-7_48

Cited by 22 publications

(8 citation statements)

References 17 publications

(24 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, heterogeneous differential privacy was formally defined in [10] to provide user-item specific privacy requirements. There have also been other efforts to model user-specific privacy requirements [29]- [32]. [29]- [31].…”

Section: Related Workmentioning

confidence: 99%

“…There have also been other efforts to model user-specific privacy requirements [29]- [32]. [29]- [31]. For instance, [29] provides partitioning mechanism to group users with personalized privacy requirements into different ǫ partitions under a non-federated setting.…”

Section: Related Workmentioning

confidence: 99%

“…[29]- [31]. For instance, [29] provides partitioning mechanism to group users with personalized privacy requirements into different ǫ partitions under a non-federated setting. Separately, there has been much work on continual learning, where the key idea is to accumulate knowledge without forgetting previously learned behavior [13]- [15], [17], [18].…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy

Chathoth,

Jagannatha,

Lee

2021

Preprint

View full text Add to dashboard Cite

Internet of Things (IoT) devices are becoming increasingly popular and are influencing many application domains such as healthcare and transportation. These devices are used for real-world applications such as sensor monitoring, real-time control. In this work, we look at differentially private (DP) neural network (NN) based network intrusion detection systems (NIDS) to detect intrusion attacks on networks of such IoT devices. Existing NN training solutions in this domain either ignore privacy considerations or assume that the privacy requirements are homogeneous across all users. We show that the performance of existing differentially private stochastic methods degrade for clients with non-identical data distributions when clients' privacy requirements are heterogeneous. We define a cohortbased (ǫ, δ)-DP framework that models the more practical setting of IoT device cohorts with non-identical clients and heterogeneous privacy requirements. We propose two novel continual-learning based DP training methods that are designed to improve model performance in the aforementioned setting. To the best of our knowledge, ours is the first system that employs a continual learning-based approach to handle heterogeneity in client privacy requirements. We evaluate our approach on real datasets and show that our techniques outperform the baselines. We also show that our methods are robust to hyperparameter changes. Lastly, we show that one of our proposed methods can easily adapt to post-hoc relaxations of client privacy requirements.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy

Chathoth,

Jagannatha,

Lee

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Data owners may have different pri vacy preferences and the same privacy preserving provided for all individuals will limit the accuracy of the model. Therefore, Li et al [57] proposed the privacyaware mechanism and utility based partitioning mechanism to acquire a better performance. The former is to minimize the waste of privacy budget whereas the latter is to maximize the utility for a given aggregate analysis.…”

Section: ) Differentially Private Ermmentioning

confidence: 99%

A Survey on Differentially Private Machine Learning [Review Article]

Gong

Xie

Pan

et al. 2020

IEEE Comput. Intell. Mag.

View full text Add to dashboard Cite

R ecent years have witnessed re markable successes of machine learning in various applications. However, machine learning models suffer from a potential risk of leaking private information contained in training data, which have attracted increasing research attention. As one of the mainstream priva cypreserving techniques, differential pri vacy provides a promising way to prevent the leaking of individuallevel privacy in training data while preserving the quality of training data for model building. This work provides a comprehensive survey on the existing works that incorporate differ ential privacy with machine learning, socalled differentially private machine learning and categorizes them into two broad categories as per different differen tial privacy mechanisms: the Laplace/ Gaussian/exponential mechanism and the output/objective perturbation mecha nism. In the former, a calibrated amount of noise is added to the nonprivate model and in the latter, the output or the objective function is perturbed by ran dom noise. Particularly, the survey covers the techniques of differentially private deep learning to alleviate the recent con cerns about the privacy of big data con tributors. In addition, the research challenges in terms of model utility, priva cy level and applications are discussed. To tackle these challenges, several potential future research directions for differentially private machine learning are pointed out.

show abstract

“…Second, perturbing the entire database (e.g., sufficient statistics) might be useful for hypothesis testing and D ----------------machine learning but individual trajectories of the medical records might be destroyed. A recent study proposes the concept of "personalized privacy" [15], which allows individuals to set their own thresholds to determine the degree of protection. However, these methods do not consider the "event-level privacy" of individual patients as the methods do not discriminate different events of individual patients' EHRs.…”

Section: Introductionmentioning

confidence: 99%

Are My EHRs Private Enough? Event-Level Privacy Protection

Mao

Zhao

Sun

et al. 2019

IEEE/ACM Trans. Comput. Biol. and Bioinf.

View full text Add to dashboard Cite

Privacy is a major concern in sharing human subject data to researchers for secondary analyses. A simple binary consent (opt-in or not) may significantly reduce the amount of sharable data, since many patients might only be concerned about a few sensitive medical conditions rather than the entire medical records. We propose event-level privacy protection, and develope a feature ablation method to protect event-level privacy in electronic medical records. Using a list of 13 sensitive diagnoses, we evaluate the feasibility and the efficacy of the proposed method. As feature ablation progresses, the identifiability of a sensitive medical condition decreases with varying speeds on different diseases. We find that these sensitive diagonoses can be divided into 3 categories: (1) 5 diseases have fast declining identifiability (AUC below 0.6 with less than 400 features excluded); (2) 7 diseases with progressively declining identifiability (AUC below 0.7 with between 200 and 700 features excluded); and (3) 1 disease with slowly declining identifiability (AUC above 0.7 with 1000 features excluded). The fact that the majority (12 out of 13) of the sensitive diseases fall into the first two categories suggests the potential of the proposed feature ablation method as a solution for event-level record privacy protection.

show abstract

Partitioning-Based Mechanisms Under Personalized Differential Privacy

Cited by 22 publications

References 17 publications

Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy

Federated Intrusion Detection for IoT with Heterogeneous Cohort Privacy

A Survey on Differentially Private Machine Learning [Review Article]

Are My EHRs Private Enough? Event-Level Privacy Protection

Contact Info

Product

Resources

About