Related papers: HARMONIC: Harnessing LLMs for Tabular Data Synthes…
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…
Fine-tuning of Large Language Models (LLMs) has become the default practice for improving model performance on a given task. However, performance improvement comes at the cost of training on vast amounts of annotated data which could be…
Large Language Models (LLMs) have empowered generative recommendation systems through fine-tuning user behavior data. However, utilizing the user data may pose significant privacy risks, potentially leading to ethical dilemmas and…
Local differential privacy (LDP) has become a prominent notion for privacy-preserving data collection. While numerous LDP protocols and post-processing (PP) methods have been developed, selecting an optimal combination under different…
The popularity of Deep Learning (DL) makes the privacy of sensitive data more imperative than ever. As a result, various privacy-preserving techniques have been implemented to preserve user data privacy in DL. Among various…
Differential privacy is a promising privacy-preserving paradigm for statistical query processing over sensitive data. It works by injecting random noise into each query result, such that it is provably hard for the adversary to infer the…
The proliferation of visual sensors in smart home environments, particularly through wearable devices like smart glasses, introduces profound privacy challenges. Existing privacy controls are often static and coarse-grained, failing to…
A key promise of machine learning is the ability to assist users with personal tasks. Because the personal context required to make accurate predictions is often sensitive, we require systems that protect privacy. A gold standard…
Conducting supervised and preference fine-tuning of large language models (LLMs) requires high-quality datasets to improve their ability to follow instructions and align with human preferences and values. However, constructing such datasets…
Introduction: The amount of data generated by original research is growing exponentially. Publicly releasing them is recommended to comply with the Open Science principles. However, data collected from human participants cannot be released…
Synthetic Electronic Health Records (EHRs) offer a valuable opportunity to create privacy preserving and harmonized structured data, supporting numerous applications in healthcare. Key benefits of synthetic data include precise control over…
Machine learning development critically depends on access to high-quality data. However, increasing restrictions due to privacy, proprietary interests, and ethical concerns have created significant barriers to data accessibility. Synthetic…
Tabular data synthesis using diffusion models has gained significant attention for its potential to balance data utility and privacy. However, existing privacy evaluations often rely on heuristic metrics or weak membership inference attacks…
Recent advancements in generative large language models (LLMs) have enabled wider applicability, accessibility, and flexibility. However, their reliability and trustworthiness are still in doubt, especially for concerns regarding…
Sequential multi-agent large language model (LLM) systems are increasingly deployed in sensitive domains such as healthcare, finance, and enterprise decision-making, where multiple specialized agents collaboratively process a single user…
Insider threats wield an outsized influence on organizations, disproportionate to their small numbers. This is due to the internal access insiders have to systems, information, and infrastructure. %One example of this influence is where…
Federated learning (FL) provides a privacy-preserving solution for fine-tuning pre-trained large language models (LLMs) using distributed private datasets, enabling task-specific adaptation while preserving data privacy. However,…
Federated Learning (FL) solutions with central Differential Privacy (DP) have seen large improvements in their utility in recent years arising from the matrix mechanism, while FL solutions with distributed (more private) DP have lagged…
Synthetic healthcare data generation offers a promising solution to research limitations in clinical settings caused by privacy and regulatory constraints. However, current synthetic data generation approaches require specialized knowledge…
Recent advances in generating synthetic data that allow to add principled ways of protecting privacy -- such as Differential Privacy -- are a crucial step in sharing statistical information in a privacy preserving way. But while the focus…