Related papers: Enhancing Data Privacy in Large Language Models th…
The performance of modern machine learning systems depends on access to large, high-quality datasets, often sourced from user-generated content or proprietary, domain-specific corpora. However, these rich datasets inherently contain…
We study the inherent trade-offs in minimizing privacy risks and maximizing utility, while maintaining high computational efficiency, when fine-tuning large language models (LLMs). A number of recent works in privacy research have attempted…
Natural language processing models have experienced a significant upsurge in recent years, with numerous applications being built upon them. Many of these applications require fine-tuning generic base models on customized, proprietary…
Large language models (LLMs), renowned for their impressive capabilities in various tasks, have significantly advanced artificial intelligence. Yet, these advancements have raised growing concerns about privacy and security implications. To…
This work investigates the effectiveness of different pseudonymization techniques, ranging from rule-based substitutions to using pre-trained Large Language Models (LLMs), on a variety of datasets and models used for two widely used NLP…
Large language models (LLMs) have become the backbone of modern natural language processing but pose privacy concerns about leaking sensitive training data. Membership inference attacks (MIAs), which aim to infer whether a sample is…
Multimodal large language models (MLLMs) have demonstrated remarkable capabilities in processing and reasoning over diverse modalities, but their advanced abilities also raise significant privacy concerns, particularly regarding Personally…
Responsible use of AI demands that we protect sensitive information without undermining the usefulness of data, an imperative that has become acute in the age of large language models. We address this challenge with an on-premise,…
Scaling laws have emerged as important components of large language model (LLM) training as they can predict performance gains through scale, and provide guidance on important hyper-parameter choices that would otherwise be expensive. LLMs…
Local differential privacy (LDP) is a strong privacy standard that has been adopted by popular software systems. The main idea is that each individual perturbs their own data locally, and only submits the resulting noisy version to a data…
The rapid development of large language models (LLMs) is redefining the landscape of human-computer interaction, and their integration into various user-service applications is becoming increasingly prevalent. However, transmitting user…
As large language models (LLMs) are integrated into sociotechnical systems, it is crucial to examine the privacy biases they exhibit. We define privacy bias as the appropriateness value of information flows in responses from LLMs. A…
The discourse on privacy risks in Large Language Models (LLMs) has disproportionately focused on verbatim memorization of training data, while a constellation of more immediate and scalable privacy threats remain underexplored. This…
Model merging is a widespread technology in large language models (LLMs) that integrates multiple task-specific LLMs into a unified one, enabling the merged model to inherit the specialized capabilities of these LLMs. Most task-specific…
Alignment is a key step in developing Large Language Models (LLMs) using human feedback to ensure adherence to human values and societal norms. Dependence on human feedback raises privacy concerns about how much a labeler's preferences may…
Mixture-of-Experts (MoE) has been gaining popularity due to its successful adaptation to large language models (LLMs). In this work, we introduce Privacy-preserving Collaborative Mixture-of-Experts (PC-MoE), which leverages the sparsity of…
Large Language Models (LLMs) are increasingly deployed across multilingual applications that handle sensitive data, yet their scale and linguistic variability introduce major privacy risks. Mostly evaluated for English, this paper…
Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user's machine, alleviate some concerns, models that users can host locally are…
The growing use of Machine Learning and Artificial Intelligence (AI), particularly Large Language Models (LLMs) like OpenAI's GPT series, leads to disruptive changes across organizations. At the same time, there is a growing concern about…
Large language model (LLM) agents are increasingly deployed in personalized tasks involving sensitive, context-dependent information, where privacy violations may arise in agents' action due to the implicitness of contextual privacy.…