Related papers: Database Reconstruction Is Not So Easy and Is Diff…
We present a data analytics system that ensures accurate counts can be released with differential privacy and minimal onboarding effort while showing instances that outperform other approaches that require more onboarding effort. The…
The availability of high-fidelity energy networks brings significant value to academic and commercial research. However, such releases also raise fundamental concerns related to privacy and security as they can reveal sensitive commercial…
We consider the problem of secret protection, in which a business or organization wishes to train a model on their own data, while attempting to not leak secrets potentially contained in that data via the model. The standard method for…
We introduce the problem of releasing sensitive data under differential privacy when the privacy level is subject to change over time. Existing work assumes that privacy level is determined by the system designer as a fixed value before…
In "Differential Perspectives: Epistemic Disconnects Surrounding the US Census Bureau's Use of Differential Privacy," boyd and Sarathy argue that empirical evaluations of the Census Disclosure Avoidance System (DAS), including our published…
Collaborative learning has gained great popularity due to its benefit of data privacy protection: participants can jointly train a Deep Learning model without sharing their training sets. However, recent works discovered that an adversary…
The objective of machine learning is to extract useful information from data, while privacy is preserved by concealing information. Thus it seems hard to reconcile these competing interests. However, they frequently must be balanced when…
Data sharing enables critical advances in many research areas and business applications, but it may lead to inadvertent disclosure of sensitive summary statistics (e.g., means or quantiles). Existing literature only focuses on protecting a…
Data stewards and analysts can promote transparent and trustworthy science and policy-making by facilitating assessments of the sensitivity of published results to alternate analysis choices. For example, researchers may want to assess…
Differential privacy (DP) is a widely applied paradigm for releasing data while maintaining user privacy. Its success is to a large part due to its composition property that guarantees privacy even in the case of multiple data releases.…
Statistical disclosure control (SDC) was not created in a single seminal paper nor following the invention of a new mathematical technique, rather it developed slowly in response to the practical challenges faced by data practitioners based…
The re-identification or de-anonymization of users from anonymized data through matching with publicly-available correlated user data has raised privacy concerns, leading to the complementary measure of obfuscation in addition to…
The main objective of data mining is to extract previously unknown patterns from large collection of data. With the rapid growth in hardware, software and networking technology there is outstanding growth in the amount data collection.…
In a backdoor attack, an adversary inserts maliciously constructed backdoor examples into a training set to make the resulting model vulnerable to manipulation. Defending against such attacks typically involves viewing these inserted…
Within the machine learning community, reconstruction attacks are a principal attack of concern and have been identified even in federated learning, which was designed with privacy preservation in mind. In federated learning, it has been…
The distributed nature of local differential privacy (LDP) invites data poisoning attacks and poses unforeseen threats to the underlying LDP-supported applications. In this paper, we propose a comprehensive mitigation framework for popular…
Large organizations such as social media companies continually release data, for example user images. At the same time, these organizations leverage their massive corpora of released data to train proprietary models that give them an edge…
The availability of rich and vast data sources has greatly advanced machine learning applications in various domains. However, data with privacy concerns comes with stringent regulations that frequently prohibited data access and data…
Statistical agencies face a dual mandate to publish accurate statistics while protecting respondent privacy. Increasing privacy protection requires decreased accuracy. Recognizing this as a resource allocation problem, we propose an…
To prove that a dataset is sufficiently anonymized, many privacy policies suggest that a re-identification risk assessment be performed, but do not provide a precise methodology for doing so, leaving the industry alone with the problem.…