相关论文: AVEC: Bootstrapping Privacy for Local LLMs

Global financial crime activity is driving demand for machine learning solutions in fraud prevention. However, prevention systems are commonly serviced to financial institutions in isolation, and few provisions exist for data sharing due to…

Large Language Model (LLM) agents provide powerful automation capabilities, but they also create a substantially broader attack surface than traditional applications due to their tight integration with non-deterministic models and…

Large Language Models (LLMs) have transformed natural language processing (NLP) by enabling robust text generation and understanding. However, their deployment in sensitive domains like healthcare, finance, and legal services raises…

Contemporary AI governance frameworks rely heavily on post hoc oversight, policy guidance, and behavioral alignment techniques, yet these mechanisms become fragile as systems gain autonomy, speed, and operational opacity. This paper…

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…

Sequential latent-variable models with subject-specific random effects provide a flexible framework for modeling temporally structured data with both local latent dynamics and stable between-subject heterogeneity. In such models,…

Speech emotion sensing in communication networks has a wide range of applications in real life. In these applications, voice data are transmitted from the user to the central server for storage, processing, and decision making. However,…

Pre-trained Large Language Models (LLMs) are an integral part of modern AI that have led to breakthrough performances in complex AI tasks. Major AI companies with expensive infrastructures are able to develop and train these large models…

With the proliferation of training data, distributed machine learning (DML) is becoming more competent for large-scale learning tasks. However, privacy concerns have to be given priority in DML, since training data may contain sensitive…

Large and well-annotated datasets are essential for advancing deep learning applications, however often costly or impossible to obtain by a single entity. In many areas, including the medical domain, approaches relying on data sharing have…

Large language models (LLMs) are increasingly applied in fields such as finance, education, and governance due to their ability to generate human-like text and adapt to specialized tasks. However, their widespread adoption raises critical…

The rapid advancement of large language models (LLMs) has enabled an emergence of agentic artificial intelligence (AI) with powerful reasoning and autonomous decision-making capabilities. This integration with edge computing has led to the…

In this work, we investigate the challenging problem of on-demand federated learning (FL) over heterogeneous edge devices with diverse resource constraints. We propose a cost-adjustable FL framework, named AnycostFL, that enables diverse…

Federated learning (FL) enables collaborative model training without sharing raw data, offering a promising path toward privacy preserving artificial intelligence. However, FL models may still memorize sensitive information from…

Federated learning (FL) enables distributed resource-constrained devices to jointly train shared models while keeping the training data local for privacy purposes. Vertical FL (VFL), which allows each client to collect partial features, has…

Local differential privacy (LDP) enables private data sharing and analytics without the need for a trusted data collector. Error-optimal primitives (for, e.g., estimating means and item frequencies) under LDP have been well studied. For…

Federated Language Model (FedLM) allows a collaborative learning without sharing raw data, yet it introduces a critical vulnerability, as every untrustworthy client may leak the received functional model instance. Current watermarking…

This paper presents two methodological advancements in decentralized multi-task learning under privacy constraints, aiming to pave the way for future developments in next-generation Blockchain platforms. First, we expand the existing…

Retrieval-Augmented Generation (RAG) has recently emerged as a promising solution for enhancing the accuracy and credibility of Large Language Models (LLMs), particularly in Question & Answer tasks. This is achieved by incorporating…

End users face a choice between privacy and efficiency in current Large Language Model (LLM) service paradigms. In cloud-based paradigms, users are forced to compromise data locality for generation quality and processing speed. Conversely,…