Search

Acquiring and aggregating data from a group of individuals is crucial for studying their general behavior. Differentially Private (DP) techniques, characterized by the parameter ϵ, help to protect Individually Identifiable Data (IID) of individuals participating in such data collection. However, such techniques affect the usefulness of the data leading to a trade-off between usefulness and privacy, thereby making the selection of ϵ an important problem before data acquisition. In this work, we use a mathematical formalism to estimate usefulness and privacy for sum query as aggregate analysis for the local model of privacy. The mathematical relation enables the application of a variety of optimization techniques, discussed in the work, to select an optimal value of ϵ. Existing methods for selecting ϵ are based on financial parameters, but they heavily rely on past data and domain knowledge which may not be available in many cases. To address this, we have provided Knee-point based recommendations along with a selection criterion to choose the method of recommendation depending on the availability of information. This allows analysts to take enlightened decisions while negotiating the value of ϵ. Our experiments on synthetic and real-world datasets unambiguously demonstrate the strength of the mathematical model and the recommended values

Differential privacy (DP) techniques provide important mathematical guarantees of privacy and in particular local DP mechanisms used to protect individual privacy without needing to trust any external entity. However, validation of these techniques is usually carried out using static datasets since IoT devices generating real-time streaming data pose additional difficulties. Hence, current work aims to validate the effectiveness of one such scheme, Privacy-Preserving Endpoint Aggregation (PPEA), on real-time private data obtained from resource-constrained edge devices by measuring utility metrics for the average operation aggregate function. This paper aims to study the feasibility of implementing PPEA for periodic real-time heart rate collection from fitness trackers, which are pervasive IoT devices within the personal healthcare domain capable of recording individual's private data, by considering factors like memory consumption, execution time, and power consumption. We address challenges concerning resource limitations on edge devices regarding lacking out-of-the-box provisions for implementing randomization techniques to achieve DP on streaming data.

For the success of any software system thorough testing and verification is very important. The acceptance of the software by the users and the term for usage depends on how well it works. For this purpose testing is an essential step. However, testing to find defects or bugs is time- consuming, expensive and has a high possibility of human error. In Automated testing, software tools are used to run detailed, repetitive, and data-intensive tests automatically. In this work we focus on identifying best tool for testing a Dynamic and Configurable web app. We provide a thorough literature survey of the various testing tools available for testing MEAN (Mongo Express Angular Node) applications. As a part of this work an Automation Test Suite is developed to test Dynamic and Configurable MEAN application.

The ability to analyze personal data for a group of individuals without compromising their respective privacy has been a focus of significant research in recent years. For such analyses, data analysts need to acquire data from individuals without revealing their Individually Identifiable Data (IID). Well established Differentially Private techniques, characterized by privacy parameters ( ϵ , δ ) , transform the data to protect the IID. However, such transformations adversely affect the usefulness of data leading to a trade-off between usefulness and privacy. Therefore, negotiating appropriate values of privacy parameters before data acquisition is a challenging task for data analysts. Most of the work, in selecting values of privacy parameters, is either based on constraining all other parameters or they provide a set of acceptable values. Here also the problem of selecting the best value from the set of acceptable values is left to the analyst. A major contribution of this paper is the method of identifying the best value of privacy parameters in a trade-off between usefulness and privacy by introducing a cost-based model, thereby addressing the issue. To enable estimation of usefulness and its cost before data acquisition, we have mathematically modeled utility in terms of data and privacy parameters. We have considered standard statistical aggregates such as Sum, Mean and Standard Deviation as compared to most of the existing works that consider only Count query as aggregate analysis. The correctness of our mathematical estimation has been validated on a diverse set of synthetic and real-world datasets spanning popular data distributions.

Secure Cloud is a cloud based data storage and computation service that works on Encrypted data without inferring any knowledge out of it. However on such secure cloud in order to perform Privacy Preserving analysis it is necessary to decrypt that data and then perform Privacy Preserving transformation. The proposed solution provides a way to perform Privacy Preserving transform on secure cloud without decrypting it. This is done by applying appropriate Differential Privacy techniques along with Homomorphic transform. The experimentation results done over the encrypted data are consistent with the utility-privacy trade-off in Differential Privacy approach on plaintext which states that the utility of data decreases as the privacy increases.

Location based services (LBS) provide many valuable and important services for end users but reveal information about personal location to potentially untrustworthy service providers which could pose privacy concerns. The information about exact path followed by a person is highly personal and can be used to uniquely identify a person. Such information is known as personally identifiable information (PII). Disclosing such information can be considered as breach of privacy. Data needs to be transformed in such a way that either PII is removed or cannot be inferred preserving the accuracy of inferences at the same time. Differential Privacy [1] is a widely used techniques for removing PII from the data. It aims to provide means to maximize the accuracy of queries from statistical databases while minimizing the chances of identifying its records. This work aims at studying the impact of transforming the data on its utility. We have used two differentially privacy techniques Laplace perturbation and sliding moving average noise reduction on trajectories of taxi [2]. This dataset is used to predict the final destination (latitude and longitude) of taxi trips. These differential privacy techniques maintain the utility of this dataset along with the preservation of the trajectory privacy of individuals.