Related papers: Adaptively Private Next-Token Prediction of Large …

Differential privacy (DP) is a widely-accepted and widely-applied notion of privacy based on worst-case analysis. Often, DP classifies most mechanisms without additive noise as non-private (Dwork et al., 2014). Thus, additive noises are…

With the increasing adoption of data-hungry machine learning algorithms, personal data privacy has emerged as one of the key concerns that could hinder the success of digital transformation. As such, Privacy-Preserving Machine Learning…

Large language models (LLMs) have shown promising performance on tasks that require reasoning, such as text-to-SQL, code generation, and debugging. However, regulatory frameworks with strict privacy requirements constrain their integration…

Federated learning (FL) enhances privacy by keeping user data on local devices. However, emerging attacks have demonstrated that the updates shared by users during training can reveal significant information about their data. This has…

The current literature on memorization in Natural Language Models, especially Large Language Models (LLMs), poses severe security and privacy risks, as models tend to memorize personally identifying information (PIIs) from training data. We…

Federated learning (FL) as one of the novel branches of distributed machine learning (ML), develops global models through a private procedure without direct access to local datasets. However, access to model updates (e.g. gradient updates…

While modern machine learning models rely on increasingly large training datasets, data is often limited in privacy-sensitive domains. Generative models trained with differential privacy (DP) on sensitive data can sidestep this challenge,…

Mixture-of-Experts (MoE) has been gaining popularity due to its successful adaptation to large language models (LLMs). In this work, we introduce Privacy-preserving Collaborative Mixture-of-Experts (PC-MoE), which leverages the sparsity of…

The preservation of privacy has emerged as a critical topic in the era of artificial intelligence. However, current work focuses on user-oriented privacy, overlooking severe enterprise data leakage risks exacerbated by the…

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…

Large language models (LLMs) are increasingly being used in privacy pipelines to detect and remedy sensitive data leakage. These solutions often rely on the premise that LLMs can reliably recognize human names, one of the most important…

Large Language Models (LLMs) have achieved remarkable progress in natural language understanding, reasoning, and autonomous decision-making. However, these advancements have also come with significant privacy concerns. While significant…

We develop a privacy-preserving distributed projection least mean squares (LMS) strategy over linear multitask networks, where agents' local parameters of interest or tasks are linearly related. Each agent is interested in not only…

The increasing use of machine learning (ML) for Just-In-Time (JIT) defect prediction raises concerns about privacy leakage from software analytics data. Existing anonymization methods, such as tabular transformations and graph…

With the advancement of Large Language Models (LLMs), LLM applications have expanded into a growing number of fields. However, users with data privacy concerns face limitations in directly utilizing LLM APIs, while private deployments incur…

Federated learning promises to make machine learning feasible on distributed, private datasets by implementing gradient descent using secure aggregation methods. The idea is to compute a global weight update without revealing the…

In this work, we devise a parameter-efficient solution to bring differential privacy (DP) guarantees into adaptation of a cross-lingual speech classifier. We investigate a new frozen pre-trained adaptation framework for DP-preserving speech…

Privacy-Preserving machine learning (PPML) can help us train and deploy models that utilize private information. In particular, on-device machine learning allows us to avoid sharing raw data with a third-party server during inference.…

Federated learning enables collaborative model training across distributed clients while preserving data privacy. However, in practical deployments, device heterogeneity, non-independent, and identically distributed (Non-IID) data often…

We study the problem of privacy-preserving machine learning (PPML) for ensemble methods, focusing our effort on random forests. In collaborative analysis, PPML attempts to solve the conflict between the need for data sharing and privacy.…