Related papers: The Limits of Differential Privacy (and its Misuse…
Differential privacy is effective in sharing information and preserving privacy with a strong guarantee. As social network analysis has been extensively adopted in many applications, it opens a new arena for the application of differential…
Local differential privacy (LDP) is a recently proposed privacy standard for collecting and analyzing data, which has been used, e.g., in the Chrome browser, iOS and macOS. In LDP, each user perturbs her information locally, and only sends…
Active learning (AL) is a widely used technique for optimizing data labeling in machine learning by iteratively selecting, labeling, and training on the most informative data. However, its integration with formal privacy-preserving methods,…
Local differential privacy (LDP) is a strong notion of privacy for individual users that often comes at the expense of a significant drop in utility. The classical definition of LDP assumes that all elements in the data domain are equally…
Metric differential privacy (DP) provides heterogeneous privacy guarantees based on a distance between the pair of inputs. It is a widely popular notion of privacy since it captures the natural privacy semantics for many applications (such…
Differential Privacy (DP) was originally developed to protect privacy. However, it has recently been utilized to secure machine learning (ML) models from poisoning attacks, with DP-SGD receiving substantial attention. Nevertheless, a…
Federated Learning (FL) allows multiple participants to train machine learning models collaboratively by keeping their datasets local while only exchanging model updates. Alas, this is not necessarily free from privacy and robustness…
Machine learning models in health care are often deployed in settings where it is important to protect patient privacy. In such settings, methods for differentially private (DP) learning provide a general-purpose approach to learn models…
The increasing adoption of differential privacy (DP) leads to public-facing DP deployments by both government agencies and companies. However, real-world DP deployments often do not fully disclose their privacy guarantees, which vary…
We study the application of differential privacy in hyper-parameter tuning, a crucial process in machine learning involving selecting the best hyper-parameter from several candidates. Unlike many private learning algorithms, including the…
The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…
Differential privacy is a widely accepted formal privacy definition that allows aggregate information about a dataset to be released while controlling privacy leakage for individuals whose records appear in the data. Due to the unavoidable…
Protecting patient data privacy is a critical concern when deploying machine learning algorithms in healthcare. Differential privacy (DP) is a common method for preserving privacy in such settings and, in this work, we examine two key…
Differential privacy (DP) has been applied in deep learning for preserving privacy of the underlying training sets. Existing DP practice falls into three categories - objective perturbation, gradient perturbation and output perturbation.…
Metric Differential Privacy (mDP) builds upon the core principles of Differential Privacy (DP) by incorporating various distance metrics, which offer adaptable and context-sensitive privacy guarantees for a wide range of applications, such…
Differential privacy (DP) is a widely-accepted and widely-applied notion of privacy based on worst-case analysis. Often, DP classifies most mechanisms without additive noise as non-private (Dwork et al., 2014). Thus, additive noises are…
Government agencies typically need to take potential risks of disclosure into account whenever they publish statistics based on their data or give external researchers access to collected data. In this context, the promise of formal privacy…
OpenData movement around the globe is demanding more access to information which lies locked in public or private servers. As recently reported by a McKinsey publication, this data has significant economic value, yet its release has…
Training reliable deep learning models which avoid making overconfident but incorrect predictions is a longstanding challenge. This challenge is further exacerbated when learning has to be differentially private: protection provided to…
Differential privacy (DP) -- a principled approach to producing statistical data products with strong, mathematically provable privacy guarantees for the individuals in the underlying dataset -- has seen substantial adoption in practice…