Related papers: How reparametrization trick broke differentially-p…
Preserving privacy in contemporary NLP models allows us to work with sensitive data, but unfortunately comes at a price. We know that stricter privacy guarantees in differentially-private stochastic gradient descent (DP-SGD) generally…
Prompt privacy is crucial, especially when using online large language models (LLMs), due to the sensitive information often contained within prompts. While LLMs can enhance prompt privacy through text rewriting, existing methods primarily…
Nowadays, machine learning models and applications have become increasingly pervasive. With this rapid increase in the development and employment of machine learning models, a concern regarding privacy has risen. Thus, there is a legitimate…
Differential Privacy (DP) can be applied to raw text by exploiting the spatial arrangement of words in an embedding space. We investigate the implications of such text privatization on Language Models (LMs) and their tendency towards…
Training data privacy is a fundamental problem in modern Artificial Intelligence (AI) applications, such as face recognition, recommendation systems, language generation, and many others, as it may contain sensitive user information related…
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…
Privacy concerns have attracted increasing attention in data-driven products due to the tendency of machine learning models to memorize sensitive training data. Generating synthetic versions of such data with a formal privacy guarantee,…
Differential Privacy (DP) for text has recently taken the form of text paraphrasing using language models and temperature sampling to better balance privacy and utility. However, the geometric distortion of DP regarding the structure and…
Differential privacy (DP) allows the quantification of privacy loss when the data of individuals is subjected to algorithmic processing such as machine learning, as well as the provision of objective privacy guarantees. However, while…
Ensuring the privacy of users whose data are used to train Natural Language Processing (NLP) models is necessary to build and maintain customer trust. Differential Privacy (DP) has emerged as the most successful method to protect the…
As the tide of Big Data continues to influence the landscape of Natural Language Processing (NLP), the utilization of modern NLP methods has grounded itself in this data, in order to tackle a variety of text-based tasks. These methods…
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…
As sufficient data are not always publically accessible for model training, researchers exploit limited data with advanced learning algorithms or expand the dataset via data augmentation (DA). Conducting DA in private domain requires…
Machine learning models are increasingly made available to the masses through public query interfaces. Recent academic work has demonstrated that malicious users who can query such models are able to infer sensitive information about…
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…
Applications of Differential Privacy (DP) in NLP must distinguish between the syntactic level on which a proposed mechanism operates, often taking the form of $\textit{word-level}$ or $\textit{document-level}$ privatization. Recently,…
Privatized text rewriting with local differential privacy (LDP) is a recent approach that enables sharing of sensitive textual documents while formally guaranteeing privacy protection to individuals. However, existing systems face several…
Recent work in Differential Privacy with Natural Language Processing (DP NLP) has proposed numerous promising techniques in the form of text rewriting mechanisms. In the evaluation of these mechanisms, an often-ignored aspect is that of…
Differential privacy (DP) is a formal notion that restricts the privacy leakage of an algorithm when running on sensitive data, in which privacy-utility trade-off is one of the central problems in private data analysis. In this work, we…
Differential Privacy (DP) is an important privacy-enhancing technology for private machine learning systems. It allows to measure and bound the risk associated with an individual participation in a computation. However, it was recently…