Related papers: Bounding Membership Inference

Differential privacy (DP) techniques can be applied to the federated learning model to statistically guarantee data privacy against inference attacks to communication among the learning agents. While ensuring strong data privacy, however,…

Data engineering often requires accuracy (utility) constraints on results, posing significant challenges in designing differentially private (DP) mechanisms, particularly under stringent privacy parameter $\epsilon$. In this paper, we…

Deep learning techniques based on neural networks have shown significant success in a wide range of AI tasks. Large-scale training datasets are one of the critical factors for their success. However, when the training datasets are…

Training deep learning models with differential privacy (DP) results in a degradation of performance. The training dynamics of models with DP show a significant difference from standard training, whereas understanding the geometric…

Differential privacy is widely accepted as the de facto method for preventing data leakage in ML, and conventional wisdom suggests that it offers strong protection against privacy attacks. However, existing semantic guarantees for DP focus…

We address the problem of learning a machine learning model from training data that originates at multiple data owners while providing formal privacy guarantees regarding the protection of each owner's data. Existing solutions based on…

Differential privacy (DP) auditing aims to provide empirical lower bounds on the privacy guarantees of DP mechanisms like DP-SGD. While some existing techniques require many training runs that are prohibitively costly, recent work…

Recently issued data privacy regulations like GDPR (General Data Protection Regulation) grant individuals the right to be forgotten. In the context of machine learning, this requires a model to forget about a training data sample if…

Neural network pruning has been an essential technique to reduce the computation and memory requirements for using deep neural networks for resource-constrained devices. Most existing research focuses primarily on balancing the sparsity and…

In machine learning, privacy requirements at inference or deployment time often evolve due to changing policies, regulations, or user preferences. In this work, we aim to construct a magnitude of models to satisfy any target differential…

Artificial Intelligence (AI) models are vulnerable to information leakage of their training data, which can be highly sensitive, for example in medical imaging. Privacy Enhancing Technologies (PETs), such as Differential Privacy (DP), aim…

Fairness and privacy are two important values machine learning (ML) practitioners often seek to operationalize in models. Fairness aims to reduce model bias for social/demographic sub-groups. Privacy via differential privacy (DP)…

We derive the optimal differential privacy (DP) parameters of a mechanism that satisfies a given level of R\'enyi differential privacy (RDP). Our result is based on the joint range of two $f$-divergences that underlie the approximate and…

Training with differential privacy (DP) provides a guarantee to members in a dataset that they cannot be identified by users of the released model. However, those data providers, and, in general, the public, lack methods to efficiently…

Deep learning models have been extensively adopted in various regions due to their ability to represent hierarchical features, which highly rely on the training set and procedures. Thus, protecting the training process and deep learning…

Differential privacy (DP) has become the de facto standard of privacy preservation due to its strong protection and sound mathematical foundation, which is widely adopted in different applications such as big data analysis, graph data…

Neural networks are susceptible to privacy attacks that can extract private information of the training set. To cope, several training algorithms guarantee differential privacy (DP) by adding noise to their computation. However, DP requires…

Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information instead of real data.…

Large language models (LLMs) trained on web-scale corpora can memorize sensitive training data, posing significant privacy risks. Differential privacy (DP) has emerged as a principled framework that limits the influence of individual data…

Differential privacy (DP) in deep learning is a critical concern as it ensures the confidentiality of training data while maintaining model utility. Existing DP training algorithms provide privacy guarantees by clipping and then injecting…