Related papers: Can Differentially Private Fine-tuning LLMs Protec…

To resolve the acute problem of privacy protection and guarantee that data can be used in the context of threat intelligence, this paper considers the implementation of Differential Privacy (DP) in cybersecurity analytics. DP, which is a…

This article introduces differentially private log-location-scale (DP-LLS) regression models, which incorporate differential privacy into LLS regression through the functional mechanism. The proposed models are established by injecting…

As on-device large language model (LLM) systems become increasingly prevalent, federated fine-tuning enables advanced language understanding and generation directly on edge devices; however, it also involves processing sensitive,…

Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…

Tuning the hyperparameters of differentially private (DP) machine learning (ML) algorithms often requires use of sensitive data and this may leak private information via hyperparameter values. Recently, Papernot and Steinke (2022) proposed…

Recent research has shown that structured machine learning models such as tree ensembles are vulnerable to privacy attacks targeting their training data. To mitigate these risks, differential privacy (DP) has become a widely adopted…

The remarkable ability of language models (LMs) has also brought challenges at the interface of AI and security. A critical challenge pertains to how much information these models retain and leak about the training data. This is…

Large language models (LLMs) frequently memorize sensitive or personal information, raising significant privacy concerns. Existing variants of differential privacy stochastic gradient descent (DPSGD) inject uniform noise into every gradient…

Attacks that aim to identify the training data of public neural networks represent a severe threat to the privacy of individuals participating in the training data set. A possible protection is offered by anonymization of the training data…

In modern settings of data analysis, we may be running our algorithms on datasets that are sensitive in nature. However, classical machine learning and statistical algorithms were not designed with these risks in mind, and it has been…

Large language models trained on clinical text risk exposing sensitive patient information, yet differential privacy (DP) methods often severely degrade the diagnostic accuracy needed for deployment. Despite rapid progress in DP…

Learning with relational and network-structured data is increasingly vital in sensitive domains where protecting the privacy of individual entities is paramount. Differential Privacy (DP) offers a principled approach for quantifying privacy…

We study the application of differential privacy in hyper-parameter tuning, a crucial process in machine learning involving selecting the best hyper-parameter from several candidates. Unlike many private learning algorithms, including the…

Differential privacy is becoming a gold standard for privacy research; it offers a guaranteed bound on loss of privacy due to release of query results, even under worst-case assumptions. The theory of differential privacy is an active…

Mechanisms used in privacy-preserving machine learning often aim to guarantee differential privacy (DP) during model training. Practical DP-ensuring training methods use randomization when fitting model parameters to privacy-sensitive data…

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…

Differential privacy (DP) ensures that training a machine learning model does not leak private data. In practice, we may have access to auxiliary public data that is free of privacy concerns. In this work, we assume access to a given amount…

Automated decision systems are increasingly used to make consequential decisions in people's lives. Due to the sensitivity of the manipulated data as well as the resulting decisions, several ethical concerns need to be addressed for the…

We consider a refinement of differential privacy --- per instance differential privacy (pDP), which captures the privacy of a specific individual with respect to a fixed data set. We show that this is a strict generalization of the standard…

Positioned between pre-training and user deployment, aligning large language models (LLMs) through reinforcement learning (RL) has emerged as a prevailing strategy for training instruction following-models such as ChatGPT. In this work, we…