Related papers: Submix: Practical Private Prediction for Large-Sca…
We explore how private synthetic text can be generated by suitably prompting a large language model (LLM). This addresses a challenge for organizations like hospitals, which hold sensitive text data like patient medical records, and wish to…
This paper presents the machine learning architecture of the Snips Voice Platform, a software solution to perform Spoken Language Understanding on microprocessors typical of IoT devices. The embedded inference is fast and accurate while…
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…
Scientific collaborations benefit from collaborative learning of distributed sources, but remain difficult to achieve when data are sensitive. In recent years, privacy preserving techniques have been widely studied to analyze distributed…
Distributed machine learning paradigms, such as federated learning, have been recently adopted in many privacy-critical applications for speech analysis. However, such frameworks are vulnerable to privacy leakage attacks from shared…
We introduce a new class of attacks on machine learning models. We show that an adversary who can poison a training dataset can cause models trained on this dataset to leak significant private details of training points belonging to other…
We consider information-theoretic privacy in federated submodel learning, where a global server has multiple submodels. Compared to the privacy considered in the conventional federated submodel learning where secure aggregation is adopted…
With careful manipulation, malicious agents can reverse engineer private information encoded in pre-trained language models. Security concerns motivate the development of quantum pre-training. In this work, we propose a highly Portable…
This study addresses the issues of privacy protection and efficiency in instruction fine-tuning of large-scale language models by proposing a parameter-efficient method that integrates differential privacy noise allocation with gradient…
The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in real-world applications, label noise…
Although machine learning (ML) is widely used for predictive tasks, there are important scenarios in which ML cannot be used or at least cannot achieve its full potential. A major barrier to adoption is the sensitive nature of predictive…
Significant advancements have recently been made in large language models represented by GPT models. Users frequently have multi-round private conversations with cloud-hosted GPT models for task optimization. Yet, this operational paradigm…
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…
A private machine learning algorithm hides as much as possible about its training data while still preserving accuracy. In this work, we study whether a non-private learning algorithm can be made private by relying on an instance-encoding…
The widespread availability of large-scale code datasets has fueled the rapid development of large language models (LLMs) for code-related tasks. These datasets may include sensitive personally identifiable information (PII), which can lead…
The integration of Differential Privacy (DP) with diffusion models (DMs) presents a promising yet challenging frontier, particularly due to the substantial memorization capabilities of DMs that pose significant privacy risks. Differential…
An increasing number of companies have begun providing services that leverage cloud-based large language models (LLMs), such as ChatGPT. However, this development raises substantial privacy concerns, as users' prompts are transmitted to and…
Speech is a common input method for mobile embedded devices, but cloud-based speech recognition systems pose privacy risks. Disentanglement-based encoders, designed to safeguard user privacy by filtering sensitive information from speech…
Pre-training models with large crawled corpora can lead to issues such as toxicity and bias, as well as copyright and privacy concerns. A promising way of alleviating such concerns is to conduct pre-training with synthetic tasks and data,…
Hierarchical text classification consists in classifying text documents into a hierarchy of classes and sub-classes. Although artificial neural networks have proved useful to perform this task, unfortunately they can leak training data…