相关论文: Initialization Matters: Privacy-Utility Analysis o…

Machine learning (ML) algorithms are heavily based on the availability of training data, which, depending on the domain, often includes sensitive information about data providers. This raises critical privacy concerns. Anonymization…

The privacy leakage of the model about the training data can be bounded in the differential privacy mechanism. However, for meaningful privacy parameters, a differentially private model degrades the utility drastically when the model…

A key task in managing distributed, sensitive data is to measure the extent to which a distribution changes. Understanding this drift can effectively support a variety of federated learning and analytics tasks. However, in many practical…

Retrieval-based language models (LMs) have demonstrated improved interpretability, factuality, and adaptability compared to their parametric counterparts, by incorporating retrieved text from external datastores. While it is well known that…

Models leak information about their training data. This enables attackers to infer sensitive information about their training sets, notably determine if a data sample was part of the model's training set. The existing works empirically show…

Differential privacy is a strong notion for privacy that can be used to prove formal guarantees, in terms of a privacy budget, $\epsilon$, about how much information is leaked by a mechanism. However, implementations of privacy-preserving…

Machine learning models are prone to memorizing sensitive data, making them vulnerable to membership inference attacks in which an adversary aims to guess if an input sample was used to train the model. In this paper, we show that prior…

A major challenge in applying differential privacy to training deep neural network models is scalability.The widely-used training algorithm, differentially private stochastic gradient descent (DP-SGD), struggles with training…

Although Large Language Models (LLMs) have become increasingly integral to diverse applications, their capabilities raise significant privacy concerns. This survey offers a comprehensive overview of privacy risks associated with LLMs and…

Recent advances in neural network based language models lead to successful deployments of such models, improving user experience in various applications. It has been demonstrated that strong performance of language models comes along with…

We define On-Average KL-Privacy and present its properties and connections to differential privacy, generalization and information-theoretic quantities including max-information and mutual information. The new definition significantly…

Being able to reconstruct training data from the parameters of a neural network is a major privacy concern. Previous works have shown that reconstructing training data, under certain circumstances, is possible. In this work, we analyse such…

By inducing privacy attacks on NLP models, attackers can obtain sensitive information such as training data and model parameters, etc. Although researchers have studied, in-depth, several kinds of attacks in NLP models, they are…

The rise of connected personal devices together with privacy concerns call for machine learning algorithms capable of leveraging the data of a large number of agents to learn personalized models under strong privacy requirements. In this…

Hyperparameter tuning is a common practice in the application of machine learning but is a typically ignored aspect in the literature on privacy-preserving machine learning due to its negative effect on the overall privacy parameter. In…

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…

Differential privacy provides strong privacy guarantees for machine learning applications. Much recent work has been focused on developing differentially private models, however there has been a gap in other stages of the machine learning…

Differentially private training algorithms provide protection against one of the most popular attacks in machine learning: the membership inference attack. However, these privacy algorithms incur a loss of the model's classification…

We propose differentially private algorithms for parameter estimation in both low-dimensional and high-dimensional sparse generalized linear models (GLMs) by constructing private versions of projected gradient descent. We show that the…

We propose a general learning framework for the protection mechanisms that protects privacy via distorting model parameters, which facilitates the trade-off between privacy and utility. The algorithm is applicable to arbitrary privacy…