Related papers: DP-MGTD: Privacy-Preserving Machine-Generated Text…

Text-to-image diffusion models have been shown to suffer from sample-level memorization, possibly reproducing near-perfect replica of images that they are trained on, which may be undesirable. To remedy this issue, we develop the first…

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…

Stochastic optimization is a pivotal enabler in modern machine learning, producing effective models for various tasks. However, several existing works have shown that model parameters and gradient information are susceptible to privacy…

Differential privacy (DP) is the prevailing technique for protecting user data in machine learning models. However, deficits to this framework include a lack of clarity for selecting the privacy budget $\epsilon$ and a lack of…

The privacy concerns associated with the use of Large Language Models (LLMs) have grown recently with the development of LLMs such as ChatGPT. Differential Privacy (DP) techniques are explored in existing work to mitigate their privacy…

Fine-tuning large language models (LLMs) for specific tasks introduces privacy risks, as models may inadvertently memorise and leak sensitive training data. While Differential Privacy (DP) offers a solution to mitigate these risks, it…

Differentially private SGD (DPSGD) enables privacy-preserving training of language models, but often reduces utility, diversity, and linguistic quality. We introduce DPRefine, a three-phase method that initializes a model using data…

Text sanitization aims to rewrite parts of a document to prevent disclosure of personal information. The central challenge of text sanitization is to strike a balance between privacy protection (avoiding the leakage of personal information)…

The collection of individuals' data has become commonplace in many industries. Local differential privacy (LDP) offers a rigorous approach to preserving privacy whereby the individual privatises their data locally, allowing only their…

In the past decade analysis of big data has proven to be extremely valuable in many contexts. Local Differential Privacy (LDP) is a state-of-the-art approach which allows statistical computations while protecting each individual user's…

Differentially Private Stochastic Gradient Descent (DP-SGD) is widely used to protect training data in machine learning. Its privacy guarantee is commonly analyzed through a security game in which an adversary infers whether a target record…

Large Language Models have shown growing ability to generate fluent and coherent texts that are highly similar to the writing style of humans. Current detectors for Machine-Generated Text (MGT) perform well when they are trained and tested…

Differential privacy provides a formal approach to privacy of individuals. Applications of differential privacy in various scenarios, such as protecting users' original utterances, must satisfy certain mathematical properties. Our…

How can agents exchange information to learn while protecting privacy? Healthcare centers collaborating on clinical trials must balance knowledge sharing with safeguarding sensitive patient data. We address this challenge by using…

Large Language Models (LLMs) are gearing up to surpass human creativity. The veracity of the statement needs careful consideration. In recent developments, critical questions arise regarding the authenticity of human work and the…

Differential Privacy (DP) provides a formal privacy guarantee preventing adversaries with access to a machine learning model from extracting information about individual training points. Differentially Private Stochastic Gradient Descent…

Fine-tuning large language models (LLMs) has become an essential strategy for adapting them to specialized tasks; however, this process introduces significant privacy challenges, as sensitive training data may be inadvertently memorized and…

Interactions with online Large Language Models raise privacy issues where providers can gather sensitive information about users and their companies from the prompts. While textual prompts can be sanitized using Differential Privacy, we…

With the use of personal devices connected to the Internet for tasks such as searches and shopping becoming ubiquitous, ensuring the privacy of the users of such services has become a requirement in order to build and maintain customer…

Synthetic data generation is a key technique in modern artificial intelligence, addressing data scarcity, privacy constraints, and the need for diverse datasets in training robust models. In this work, we propose a method for generating…