Related papers: Personalized Language Model Learning on Text Data …

Recent advances in diffusion-based lip-syncing generative models have demonstrated their ability to produce highly synchronized talking face videos for visual dubbing. Although these models excel at lip synchronization, they often struggle…

The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a novel framework with textual embeddings from Pre-trained…

Training personalized speech enhancement models is innately a no-shot learning problem due to privacy constraints and limited access to noise-free speech from the target user. If there is an abundance of unlabeled noisy speech from the…

An unsolved challenge in distributed or federated learning is to effectively mitigate privacy risks without slowing down training or reducing accuracy. In this paper, we propose TextHide aiming at addressing this challenge for natural…

Text-to-image diffusion models have emerged as powerful tools for high-quality image generation and editing. Many existing approaches rely on text prompts as editing guidance. However, these methods are constrained by the need for manual…

Mobile applications increasingly rely on sensor data to infer user context and deliver personalized experiences. Yet the mechanisms behind this personalization remain opaque to users and researchers alike. This paper presents a sandbox…

In this paper, we aim to generate text classification data given arbitrary class definitions (i.e., user instruction), so one can train a small text classifier without any human annotation or raw corpus. Compared with pioneer attempts, our…

Large language models (LLMs) have significantly transformed natural language understanding and generation, but they raise privacy concerns due to potential exposure of sensitive information. Studies have highlighted the risk of information…

Using language models as a remote service entails sending private information to an untrusted provider. In addition, potential eavesdroppers can intercept the messages, thereby exposing the information. In this work, we explore the…

User-level privacy is important in distributed systems. Previous research primarily focuses on the central model, while the local models have received much less attention. Under the central model, user-level DP is strictly stronger than the…

The prevalence of biometric authentication has been on the rise due to its ease of use and elimination of weak passwords. To date, most biometric authentication systems have been designed for on-device authentication of the device owner…

Federated learning enables collaborative training of machine learning models under strict privacy restrictions and federated text-to-speech aims to synthesize natural speech of multiple users with a few audio training samples stored in…

Personalized LLMs can significantly enhance user experiences by tailoring responses to preferences such as helpfulness, conciseness, and humor. However, fine-tuning models to address all possible combinations of user preferences is…

Service providers of large language model (LLM) applications collect user instructions in the wild and use them in further aligning LLMs with users' intentions. These instructions, which potentially contain sensitive information, are…

Spoken language understanding (SLU), one of the key enabling technologies for human-computer interaction in IoT devices, provides an easy-to-use user interface. Human speech can contain a lot of user-sensitive information, such as gender,…

Anomalies or failures in large computer systems, such as the cloud, have an impact on a large number of users that communicate, compute, and store information. Therefore, timely and accurate anomaly detection is necessary for reliability,…

The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural…

The popularity of mobile device has made people's lives more convenient, but threatened people's privacy at the same time. As end users are becoming more and more concerned on the protection of their private information, it is even harder…

Embodied agents designed to assist users with tasks must engage in natural language interactions, interpret instructions, execute actions, and communicate effectively to resolve issues. However, collecting large-scale, diverse datasets of…

Large language models (LLMs) are transforming society, powering applications from smartphone assistants to autonomous driving. Yet cloud-based LLM services alone cannot serve a growing class of applications, including those operating under…