Privacy-Preserving Crowd-Sourcing of Web Searches with Private Data Donor

Primault, Vincent; Lampos, Vasileios; Cox, Ingemar J.; Cristofaro, Emiliano De

doi:10.1145/3308558.3313474

Cited by 6 publications

(2 citation statements)

References 40 publications

(71 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is also a body of work that conducts longitudinal studies on deleted web content and their subsequent information leakage [6,57]. The research in this area focuses on data leakage through social media [73,88], blogging services that publish information [83], or aggregation of web data [66]. Cloak, however, focuses on an inference-as-a-service setup where private queries that potentially contain sensitive information are sent to a web-service to run machine learning inference.…”

Section: Web-application Privacymentioning

confidence: 99%

Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy

Mireshghallah

Taram

Jalali

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

When receiving machine learning services from the cloud, the provider does not need to receive all features; in fact, only a subset of the features are necessary for the target prediction task. Discerning this subset is the key problem of this work. We formulate this problem as a gradient-based perturbation maximization method that discovers this subset in the input feature space with respect to the functionality of the prediction model used by the provider. After identifying the subset, our framework, Cloak, suppresses the rest of the features using utility-preserving constant values that are discovered through a separate gradient-based optimization process. We show that Cloak does not necessarily require collaboration from the service provider beyond its normal service, and can be applied in scenarios where we only have black-box access to the service provider's model. We theoretically guarantee that Cloak's optimizations reduce the upper bound of the Mutual Information (MI) between the data and the sifted representations that are sent out. Experimental results show that Cloak reduces the mutual information between the input and the sifted representations by 85.01% with only negligible reduction in utility (1.42%). In addition, we show that Cloak greatly diminishes adversaries' ability to learn and infer non-conducive features. CCS CONCEPTS• Security and privacy → Privacy protections; Usability in security and privacy; • Computing methodologies → Neural networks; Computer vision tasks; • Mathematics of computing → Information theory.

show abstract

Section: Web-application Privacymentioning

confidence: 99%

Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy

Mireshghallah

Taram

Jalali

et al. 2021

Proceedings of the Web Conference 2021

View full text Add to dashboard Cite

show abstract

“…From the technical view, data can be protected by the following two approaches. On one hand, we can rely on secure multiparty computation (SMC) to jointly compute a public function without mutually revealing private inputs by executing cryptographic protocols [8,43,47]. On the other hand, differential privacy (DP) [1,12,18] can be adopted by adding noises to the data, with the purpose of obfuscating the privacy properties and avoiding the user attributes to be inferred [37,51].…”

Section: Related Workmentioning

confidence: 99%

PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization

Liu

Guo

Chen

2021

Preprint

View full text Add to dashboard Cite

Federated learning (FL) has become a prevalent distributed machine learning paradigm with improved privacy. After learning, the resulting federated model should be further personalized to each different client. While several methods have been proposed to achieve personalization, they are typically limited to a single local device, which may incur bias or overfitting since data in a single device is extremely limited. In this paper, we attempt to realize personalization beyond a single client. The motivation is that during the FL process, there may exist many clients with similar data distribution, and thus the personalization performance could be significantly boosted if these similar clients can cooperate with each other. Inspired by this, this paper introduces a new concept called federated adaptation, targeting at adapting the trained model in a federated manner to achieve better personalization results. However, the key challenge for federated adaptation is that we could not outsource any raw data from the client during adaptation, due to privacy concerns. In this paper, we propose PFA, a framework to accomplish Privacy-preserving Federated Adaptation. PFA leverages the sparsity property of neural networks to generate privacy-preserving representations and uses them to efficiently identify clients with similar data distributions. Based on the grouping results, PFA conducts an FL process in a group-wise way on the federated model to accomplish the adaptation. For evaluation, we manually construct several practical FL datasets based on public datasets in order to simulate both the class-imbalance and background-difference conditions. Extensive experiments on these datasets and popular model architectures demonstrate the effectiveness of PFA, outperforming other state-of-the-art methods by a large margin while ensuring user privacy. We will release our code at: https:// github.com/ lebyni/ PFA.

show abstract

OblivSend: Secure and Ephemeral File Sharing Services with Oblivious Expiration Control

Shen

Lai

et al. 2022

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Privacy-Preserving Crowd-Sourcing of Web Searches with Private Data Donor

Cited by 6 publications

References 40 publications

Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy

Not All Features Are Equal: Discovering Essential Features for Preserving Prediction Privacy

PFA: Privacy-preserving Federated Adaptation for Effective Model Personalization

OblivSend: Secure and Ephemeral File Sharing Services with Oblivious Expiration Control

Contact Info

Product

Resources

About