相关论文: Revisiting Privacy, Utility, and Efficiency Trade-…

Federated Learning (FL) enables collaborative model training while preserving data privacy; however, balancing privacy preservation (PP) and fairness poses significant challenges. In this paper, we present the first unified large-scale…

Despite its substantial impact on various search, recommendation, and question answering tasks, privacy-preserving methods for personalizing large language models (LLMs) have received relatively limited exploration. There is one primary…

In machine learning, privacy requirements at inference or deployment time often evolve due to changing policies, regulations, or user preferences. In this work, we aim to construct a magnitude of models to satisfy any target differential…

In this paper, we focus our attention on private Empirical Risk Minimization (ERM), which is one of the most commonly used data analysis method. We take the first step towards solving the above problem by theoretically exploring the effect…

Broad adoption of machine learning techniques has increased privacy concerns for models trained on sensitive data such as medical records. Existing techniques for training differentially private (DP) models give rigorous privacy guarantees,…

The rapid advancements of large language models (LLMs) have raised public concerns about the privacy leakage of personally identifiable information (PII) within their extensive training datasets. Recent studies have demonstrated that an…

The recent success of large language models (LLMs) has been largely driven by vast public datasets. However, the next frontier for LLM development lies beyond public data. Much of the world's most valuable information is private, especially…

This study proposes a large language model optimization method based on the improved LoRA fine-tuning algorithm, aiming to improve the accuracy and computational efficiency of the model in natural language processing tasks. We fine-tune the…

Machine learning is increasingly used in the most diverse applications and domains, whether in healthcare, to predict pathologies, or in the financial sector to detect fraud. One of the linchpins for efficiency and accuracy in machine…

Large language models (LLMs) have demonstrated remarkable performance across various downstream tasks. However, the high computational and memory requirements of LLMs are a major bottleneck. To address this, parameter-efficient fine-tuning…

Large Language Models (LLMs) embed sensitive, human-generated data, prompting the need for unlearning methods. Although certified unlearning offers strong privacy guarantees, its restrictive assumptions make it unsuitable for LLMs, giving…

The safety alignment of large language models (LLMs) is becoming increasingly important with their democratization. In this paper, we study the safety degradation that comes with adapting LLMs to new tasks. We attribute this safety…

Mobile Large Language Models (LLMs) are revolutionizing diverse fields such as healthcare, finance, and education with their ability to perform advanced natural language processing tasks on-the-go. However, the deployment of these models in…

The integration of large language models (LLMs) into cyber security applications presents both opportunities and critical safety risks. We introduce CyberLLMInstruct, a dataset of 54,928 pseudo-malicious instruction-response pairs spanning…

This position paper argues that achieving robustness, privacy, and efficiency simultaneously in machine learning systems is infeasible under prevailing threat models. The tension between these goals arises not from algorithmic shortcomings…

While large language models (LLMs) often adopt finetuning to unlock their capabilities for downstream applications, our understanding on the inductive biases (especially the scaling properties) of different finetuning methods is still…

Instruction fine-tuning has emerged as a critical technique for customizing Large Language Models (LLMs) to specific applications. However, recent studies have highlighted significant security vulnerabilities in fine-tuned LLMs. Existing…

Memorization in Large Language Models (LLMs) poses privacy and security risks, as models may unintentionally reproduce sensitive or copyrighted data. Existing analyses focus on average-case scenarios, often neglecting the highly skewed…

Local Differential Privacy (LDP) offers strong privacy protection, especially in settings in which the server collecting the data is untrusted. However, designing LDP mechanisms that achieve an optimal trade-off between privacy, utility and…

The generative Artificial Intelligence (AI) tools based on Large Language Models (LLMs) use billions of parameters to extensively analyse large datasets and extract critical private information such as, context, specific details,…