相关论文: Selective Pre-training for Private Fine-tuning

The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains…

Pre-training on public data is an effective method to improve the performance for federated learning (FL) with differential privacy (DP). This paper investigates how large language models (LLMs) trained on public data can improve the…

With the rise of large language models, service providers offer language models as a service, enabling users to fine-tune customized models via uploaded private datasets. However, this raises concerns about sensitive data leakage. Prior…

In-context learning (ICL)-the ability of transformer-based models to perform new tasks from examples provided at inference time-has emerged as a hallmark of modern language models. While recent works have investigated the mechanisms…

Prompt-tuning has received attention as an efficient tuning method in the language domain, i.e., tuning a prompt that is a few tokens long, while keeping the large language model frozen, yet achieving comparable performance with…

Model adaptation is crucial to handle the discrepancy between proxy training data and actual users data received. To effectively perform adaptation, textual data of users is typically stored on servers or their local devices, where…

Fine-tuning large language models on private data for downstream applications poses significant privacy risks in potentially exposing sensitive information. Several popular community platforms now offer convenient distribution of a large…

The pre-training and fine-tuning paradigm has demonstrated its effectiveness and has become the standard approach for tailoring language models to various tasks. Currently, community-based platforms offer easy access to various pre-trained…

We identify a novel phenomenon in language models: benign fine-tuning of frontier models can lead to privacy collapse. We find that diverse, subtle patterns in training data can degrade contextual privacy, including optimisation for…

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process…

As the performance of larger, newer Large Language Models continues to improve for strategic Theory of Mind (ToM) tasks, the demand for these state-of-the-art models increases commensurately. However, their deployment is costly both in…

Recent developments in language modeling have increased their use in various applications and domains. Language models, often trained on sensitive data, can memorize and disclose this information during privacy attacks, raising concerns…

Large language models are shown to memorize privacy information such as social security numbers in training data. Given the sheer scale of the training corpus, it is challenging to screen and filter these privacy data, either manually or…

In large-scale statistical learning, data collection and model fitting are moving increasingly toward peripheral devices---phones, watches, fitness trackers---away from centralized data collection. Concomitant with this rise in…

Federated Learning allows distributed entities to train a common model collaboratively without sharing their own data. Although it prevents data collection and aggregation by exchanging only parameter updates, it remains vulnerable to…

Recent developments in natural language representations have been accompanied by large and expensive models that leverage vast amounts of general-domain text through self-supervised pre-training. Due to the cost of applying such models to…

Modern large-scale Pre-trained Language Models (PLMs) have achieved tremendous success on a wide range of downstream tasks. However, most of the LM pre-training objectives only focus on text reconstruction, but have not sought to learn…

Privacy-preserving machine learning aims to train models on private data without leaking sensitive information. Differential privacy (DP) is considered the gold standard framework for privacy-preserving training, as it provides formal…

Current LLM-based services typically require users to submit raw text regardless of its sensitivity. While intuitive, such practice introduces substantial privacy risks, as unauthorized access may expose personal, medical, or legal…

Large language models (LLMs) are primarily accessed via commercial APIs, but this often requires users to expose their data to service providers. In this paper, we explore how users can stay in control of their data by using privacy…