相关论文: Inspecting the Representation Manifold of Differen…

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…

Contextual word representations generated by language models (LMs) learn spurious associations present in the training corpora. Recent findings reveal that adversaries can exploit these associations to reverse-engineer the private…

Encoded text representations often capture sensitive attributes about individuals (e.g., race or gender), which raise privacy concerns and can make downstream models unfair to certain groups. In this work, we propose FEDERATE, an approach…

Differentially private text sanitization refers to the process of privatizing texts under the framework of Differential Privacy (DP), providing provable privacy guarantees while also empirically defending against adversaries seeking to harm…

As the use of differential privacy (DP) becomes widespread, the development of effective tools for reasoning about the privacy guarantee becomes increasingly critical. In pursuit of this goal, we demonstrate novel relationships between DP…

Texts convey sophisticated knowledge. However, texts also convey sensitive information. Despite the success of general-purpose language models and domain-specific mechanisms with differential privacy (DP), existing text sanitization…

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…

Accurately learning from user data while ensuring quantifiable privacy guarantees provides an opportunity to build better Machine Learning (ML) models while maintaining user trust. Recent literature has demonstrated the applicability of a…

Differentially private noise mechanisms commonly use symmetric noise distributions. This is attractive both for achieving the differential privacy definition, and for unbiased expectations in the noised answers. However, there are contexts…

Many works at the intersection of Differential Privacy (DP) in Natural Language Processing aim to protect privacy by transforming texts under DP guarantees. This can be performed in a variety of ways, from word perturbations to full…

We review the use of differential privacy (DP) for privacy protection in machine learning (ML). We show that, driven by the aim of preserving the accuracy of the learned models, DP-based ML implementations are so loose that they do not…

Differential privacy (DP) is a mathematical privacy notion increasingly deployed across government and industry. With DP, privacy protections are probabilistic: they are bounded by the privacy budget parameter, $\epsilon$. Prior work in…

Text rewriting with differential privacy (DP) provides concrete theoretical guarantees for protecting the privacy of individuals in textual documents. In practice, existing systems may lack the means to validate their privacy-preserving…

Machine Learning approaches to Natural Language Processing tasks benefit from a comprehensive collection of real-life user data. At the same time, there is a clear need for protecting the privacy of the users whose data is collected and…

Humans use introspection to evaluate their understanding through private internal states inaccessible to external observers. We investigate whether large language models possess similar privileged knowledge about answer correctness,…

We study the problem of differentially private (DP) mechanisms for representing sets of size $k$ from a large universe. Our first construction creates $(\epsilon,\delta)$-DP representations with error probability of $1/(e^\epsilon + 1)$…

Metric Differential Privacy (mDP) extends the concept of Differential Privacy (DP) to serve as a new paradigm of data perturbation. It is designed to protect secret data represented in general metric space, such as text data encoded as word…

To protect the privacy of individuals whose data is being shared, it is of high importance to develop methods allowing researchers and companies to release textual data while providing formal privacy guarantees to its originators. In the…

Differential Privacy (DP) provides an elegant mathematical framework for defining a provable disclosure risk in the presence of arbitrary adversaries; it guarantees that whether an individual is in a database or not, the results of a DP…

Online users generate tremendous amounts of textual information by participating in different activities, such as writing reviews and sharing tweets. This textual data provides opportunities for researchers and business partners to study…