Related papers: Synthetic Query Generation for Privacy-Preserving …
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…
Pre-training large transformer models with in-domain data improves domain adaptation and helps gain performance on the domain-specific downstream tasks. However, sharing models pre-trained on potentially sensitive data is prone to…
Retrieval-augmented generation (RAG) is a widely used framework for reducing hallucinations in large language models (LLMs) on domain-specific tasks by retrieving relevant documents from a database to support accurate responses. However,…
In recent years, local differential privacy (LDP) has emerged as a technique of choice for privacy-preserving data collection in several scenarios when the aggregator is not trustworthy. LDP provides client-side privacy by adding noise at…
Personalization in Information Retrieval (IR) is a topic studied by the research community since a long time. However, there is still a lack of datasets to conduct large-scale evaluations of personalized IR; this is mainly due to the fact…
As the use of large embedding models in recommendation systems and language applications increases, concerns over user data privacy have also risen. DP-SGD, a training algorithm that combines differential privacy with stochastic gradient…
Graphs offer unique insights into relationships between entities, complementing data modalities like text and images and enabling AI models to extend their capabilities beyond traditional tasks. However, learning from graphs often involves…
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…
Programmatically generating tight differential privacy (DP) bounds is a hard problem. Two core challenges are (1) finding expressive, compact, and efficient encodings of the distributions of DP algorithms, and (2) state space explosion…
Reinforcement learning (RL) algorithms can be used to provide personalized services, which rely on users' private and sensitive data. To protect the users' privacy, privacy-preserving RL algorithms are in demand. In this paper, we study RL…
In cross-silo federated learning (FL), sensitive text datasets remain confined to local organizations due to privacy regulations, making repeated training for each downstream task both communication-intensive and privacy-demanding. A…
Differential privacy (DP) has become the standard for private data analysis. Certain machine learning applications only require privacy protection for specific protected attributes. Using naive variants of differential privacy in such use…
The rapid advancement of large language models (LLMs) has revolutionized natural language processing, enabling applications in diverse domains such as healthcare, finance and education. However, the growing reliance on extensive data for…
Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…
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…
In the arena of privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) has outstripped the objective perturbation mechanism in popularity and interest. Though unrivaled in versatility, DP-SGD…
Motivated by the increasing deployment of reinforcement learning in the real world, involving a large consumption of personal data, we introduce a differentially private (DP) policy gradient algorithm. We show that, in this setting, the…
Differential privacy (DP) is applied when fine-tuning pre-trained large language models (LLMs) to limit leakage of training examples. While most DP research has focused on improving a model's privacy-utility tradeoff, some find that DP can…
Institutions collect massive learning traces but they may not disclose it for privacy issues. Synthetic data generation opens new opportunities for research in education. In this paper we present a generative model for educational data that…
One of the big challenges in machine learning applications is that training data can be different from the real-world data faced by the algorithm. In language modeling, users' language (e.g. in private messaging) could change in a year and…