Privacy-Preserving Adversarial Networks

Tripathy, Ardhendu; Wang, Ye; Ishwar, Prakash

doi:10.1109/allerton.2019.8919758

Cited by 59 publications

(50 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The discriminator aims to maximize an objective function in minimax game that the generator aims to minimize. GANs have also been applied for enhancing privacy [9,14]. For example, to protect health records, synthetic medical datasets can be published instead of the real ones using generative models training on sensitive real-world medical datasets [3,6].…”

Section: Related Work and Discussionmentioning

confidence: 99%

Protecting Sensory Data against Sensitive Inferences

Malekzadeh

Clegg

Cavallaro

et al. 2018

Proceedings of the 1st Workshop on Privacy by Design in Distributed Systems

140

View full text Add to dashboard Cite

There is growing concern about how personal data are used when users grant applications direct access to the sensors of their mobile devices. In fact, high resolution temporal data generated by motion sensors reflect directly the activities of a user and indirectly physical and demographic attributes. In this paper, we propose a feature learning architecture for mobile devices that provides flexible and negotiable privacy-preserving sensor data transmission by appropriately transforming raw sensor data. The objective is to move from the current binary setting of granting or not permission to an application, toward a model that allows users to grant each application permission over a limited range of inferences according to the provided services. The internal structure of each component of the proposed architecture can be flexibly changed and the trade-off between privacy and utility can be negotiated between the constraints of the user and the underlying application. We validated the proposed architecture in an activity recognition application using two real-world datasets, with the objective of recognizing an activity without disclosing gender as an example of private information. Results show that the proposed framework maintains the usefulness of the transformed data for activity recognition, with an average loss of only around three percentage points, while reducing the possibility of gender classification to around 50%, the target random guess, from more than 90% when using raw sensor data. We also present and distribute MotionSense, a new dataset for activity and attribute recognition collected from motion sensors.

show abstract

Section: Related Work and Discussionmentioning

confidence: 99%

Protecting Sensory Data against Sensitive Inferences

Malekzadeh

Clegg

Cavallaro

et al. 2018

Proceedings of the 1st Workshop on Privacy by Design in Distributed Systems

140

View full text Add to dashboard Cite

show abstract

“…For example, Li and Oechtering [40] proposed a new privacy metric based on distributed Bayesian detection which can inform privacyaware system design. Recently, Tripathy et al [41] and Huang et al [42] used adversarial networks for designing privacy-assuring mappings that navigate the PUT. Takbiri et al [43] considered obfuscation and anonymization techniques and characterized the conditions required to obtain perfect privacy.…”

Section: Related Workmentioning

confidence: 99%

Privacy With Estimation Guarantees

Wang

Calmon

et al. 2019

IEEE Trans. Inform. Theory

View full text Add to dashboard Cite

We study the central problem in data privacy: how to share data with an analyst while providing both privacy and utility guarantees to the user that owns the data. In this setting, we present an estimation-theoretic analysis of the privacy-utility trade-off (PUT). Here, an analyst is allowed to reconstruct (in a mean-squared error sense) certain functions of the data (utility), while other private functions should not be reconstructed with distortion below a certain threshold (privacy). We demonstrate how χ 2 -information captures the fundamental PUT in this case and provide bounds for the best PUT. We propose a convex program to compute privacy-assuring mappings when the functions to be disclosed and hidden are known a priori and the data distribution is known. We derive lower bounds on the minimum mean-squared error of estimating a target function from the disclosed data and evaluate the robustness of our approach when an empirical distribution is used to compute the privacy-assuring mappings instead of the true data distribution. We illustrate the proposed approach through two numerical experiments.Index Terms-Estimation, privacy-utility trade-off, minimum mean-squared error.

show abstract

“…where P indicates privacy, D and D represent any two neighbouring datasets that have only a single different element, T denotes a set of tuples, and represents the privacy budget. Whereas, the privacy budget is an important factor in differential privacy which ranges from 0 (minimum-) to 1 (maximum-) [14].…”

Section: Differential Privacymentioning

confidence: 99%

FedOpt: Towards Communication Efficiency and Privacy Preservation in Federated Learning

2020

View full text Add to dashboard Cite

Artificial Intelligence (AI) has been applied to solve various challenges of real-world problems in recent years. However, the emergence of new AI technologies has brought several problems, especially with regard to communication efficiency, security threats and privacy violations. Towards this end, Federated Learning (FL) has received widespread attention due to its ability to facilitate the collaborative training of local learning models without compromising the privacy of data. However, recent studies have shown that FL still consumes considerable amounts of communication resources. These communication resources are vital for updating the learning models. In addition, the privacy of data could still be compromised once sharing the parameters of the local learning models in order to update the global model. Towards this end, we propose a new approach, namely, Federated Optimisation (FedOpt) in order to promote communication efficiency and privacy preservation in FL. In order to implement FedOpt, we design a novel compression algorithm, namely, Sparse Compression Algorithm (SCA) for efficient communication, and then integrate the additively homomorphic encryption with differential privacy to prevent data from being leaked. Thus, the proposed FedOpt smoothly trade-offs communication efficiency and privacy preservation in order to adopt the learning task. The experimental results demonstrate that FedOpt outperforms the state-of-the-art FL approaches. In particular, we consider three different evaluation criteria; model accuracy, communication efficiency and computation overhead. Then, we compare the proposed FedOpt with the baseline configurations and the state-of-the-art approaches, i.e., Federated Averaging (FedAvg) and the paillier-encryption based privacy-preserving deep learning (PPDL) on all these three evaluation criteria. The experimental results show that FedOpt is able to converge within fewer training epochs and a smaller privacy budget.

show abstract

Privacy-Preserving Adversarial Networks

Cited by 59 publications

References 23 publications

Protecting Sensory Data against Sensitive Inferences

Protecting Sensory Data against Sensitive Inferences

Privacy With Estimation Guarantees

FedOpt: Towards Communication Efficiency and Privacy Preservation in Federated Learning

Contact Info

Product

Resources

About