Related papers: Inside the Black Box: Detecting Data Leakage in Pr…
As large language models (LLMs) become progressively more embedded in clinical decision-support, documentation, and patient-information systems, ensuring their privacy and trustworthiness has emerged as an imperative challenge for the…
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…
We investigate the contents of web-scraped data for training AI systems, at sizes where human dataset curators and compilers no longer manually annotate every sample. Building off of prior privacy concerns in machine learning models, we…
The use of personal data for training machine learning systems comes with a privacy threat and measuring the level of privacy of a model is one of the major challenges in machine learning today. Identifying training data based on a trained…
Differential privacy (DP) is a formal privacy framework that enables training machine learning (ML) models while protecting individuals' data. As pointed out by prior work, ML models are part of larger systems, which can lead to so-called…
Large language models (LLMs) have significantly transformed the landscape of Natural Language Processing (NLP). Their impact extends across a diverse spectrum of tasks, revolutionizing how we approach language understanding and generations.…
The advent of Large Language Models (LLMs) has garnered significant popularity and wielded immense power across various domains within Natural Language Processing (NLP). While their capabilities are undeniably impressive, it is crucial to…
In this paper we develop state-of-the-art privacy attacks against Large Language Models (LLMs), where an adversary with some access to the model tries to learn something about the underlying training data. Our headline results are new…
Pre-trained Transformers are challenging human performances in many NLP tasks. The massive datasets used for pre-training seem to be the key to their success on existing tasks. In this paper, we explore how a range of pre-trained Natural…
How much information about training samples can be leaked through synthetic data generated by Large Language Models (LLMs)? Overlooking the subtleties of information flow in synthetic data generation pipelines can lead to a false sense of…
This paper investigates the potential privacy risks associated with forecasting models, with specific emphasis on their application in the context of smart grids. While machine learning and deep learning algorithms offer valuable utility,…
Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language…
Protecting privacy in contemporary NLP models is gaining in importance. So does the need to mitigate social biases of such models. But can we have both at the same time? Existing research suggests that privacy preservation comes at the…
Pre-trained language models (PLMs) have demonstrated significant proficiency in solving a wide range of general natural language processing (NLP) tasks. Researchers have observed a direct correlation between the performance of these models…
Large multimodal language models have proven transformative in numerous applications. However, these models have been shown to memorize and leak pre-training data, raising serious user privacy and information security concerns. While data…
Sequence models, such as Large Language Models (LLMs) and autoregressive image generators, have a tendency to memorize and inadvertently leak sensitive information. While this tendency has critical legal implications, existing tools are…
Adapting pre-trained deep learning models to customized tasks has become a popular choice for developers to cope with limited computational resources and data volume. More specifically, probing--training a downstream head on a pre-trained…
Differential privacy (DP) is applied when fine-tuning pre-trained large language models (LLMs) to limit leakage of training examples. While most DP research has focused on improving a model's privacy-utility tradeoff, some find that DP can…
Recent years have witnessed significant progress in developing deep learning-based models for automated code completion. Although using source code in GitHub has been a common practice for training deep-learning-based models for code…
Large Language Models (LLMs) are increasingly deployed in mental health contexts, from structured therapeutic support tools to informal chat-based well-being assistants. While these systems increase accessibility, scalability, and…