相关论文: PILLAR: an AI-Powered Privacy Threat Modeling Tool

With the increasing prevalence of mental health conditions worldwide, AI-powered chatbots and conversational agents have emerged as accessible tools to support mental health. However, deploying Large Language Models (LLMs) in mental…

Large Language Models (LLMs) have revolutionized how information are collected, aggregated, and reasoned. However, this enables a novel and accessible vector of privacy intrusion: the automated and in-depth personal profiling; this…

The increasing deployment of Machine Learning (ML) models in sensitive domains motivates the need for robust, practical privacy assessment tools. PrivacyGuard is a comprehensive tool for empirical differential privacy (DP) analysis,…

Fine-tuning unlocks large language models (LLMs) for specialized applications, but its high computational cost often puts it out of reach for resource-constrained organizations. While cloud platforms could provide the needed resources, data…

Research and development of privacy analysis tools currently suffers from a lack of test beds for evaluation and comparison of such tools. In this work, we propose a benchmark application that implements an extensive list of privacy…

Privacy policies are often obfuscated by their complexity, which impedes transparency and informed consent. Conventional machine learning approaches for automatically analyzing these policies demand significant resources and substantial…

Large language models (LLMs) have achieved remarkable success and are widely adopted for diverse applications. However, fine-tuning these models often involves private or sensitive information, raising critical privacy concerns. In this…

The proliferation of large AI models trained on uncurated, often sensitive web-scraped data has raised significant privacy concerns. One of the concerns is that adversaries can extract information about the training data using privacy…

As Large Language Models (LLMs) become integral to scientific workflows, concerns over the confidentiality and ethical handling of confidential data have emerged. This paper explores data exposure risks through LLM-powered scientific tools,…

The advancement of Large Language Models (LLMs) has significantly impacted various domains, including Web search, healthcare, and software development. However, as these models scale, they become more vulnerable to cybersecurity risks,…

Artificial Intelligence have profoundly transformed the technological landscape in recent years. Large Language Models (LLMs) have demonstrated impressive abilities in reasoning, text comprehension, contextual pattern recognition, and…

Large Language Models (LLMs) are increasingly adopted across domains such as education, healthcare, and finance. In healthcare, LLMs support tasks including disease diagnosis, abnormality classification, and clinical decision-making. Among…

Large Language Model (LLM) systems are inherently compositional, with individual LLM serving as the core foundation with additional layers of objects such as plugins, sandbox, and so on. Along with the great potential, there are also…

This paper introduces a novel privacy-preservation framework named PFID for LLMs that addresses critical privacy concerns by localizing user data through model sharding and singular value decomposition. When users are interacting with LLM…

This paper presents a novel application of large language models (LLMs) to enhance user comprehension of privacy policies through an interactive dialogue agent. We demonstrate that LLMs significantly outperform traditional models in tasks…

The proliferation of visual sensors in smart home environments, particularly through wearable devices like smart glasses, introduces profound privacy challenges. Existing privacy controls are often static and coarse-grained, failing to…

Machine learning has become a crucial part of our lives, with applications spanning nearly every aspect of our daily activities. However, using personal information in machine learning applications has sparked significant security and…

The proliferation of Large Language Models (LLMs) has driven considerable interest in fine-tuning them with domain-specific data to create specialized language models. Nevertheless, such domain-specific fine-tuning data often contains…

Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains lacking. We present SafeLM, a framework that jointly addresses four pillars of LLM safety:…

Inspired by the rapid development of Large Language Models (LLMs), LLM agents have evolved to perform complex tasks. LLM agents are now extensively applied across various domains, handling vast amounts of data to interact with humans and…