相关论文: From Weak Cues to Real Identities: Evaluating Infe…

AI agents augment large language models with external tools such as web retrieval, enabling grounded and up-to-date responses. However, incorporating external content into the generation pipeline can weaken the safety alignment mechanisms…

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…

Large language models (LLMs) have demonstrated significant potential in developing Role-Playing Agents (RPAs). However, current research primarily evaluates RPAs using famous fictional characters, allowing models to rely on memory…

Good training data is a prerequisite to develop useful ML applications. However, in many domains existing data sets cannot be shared due to privacy regulations (e.g., from medical studies). This work investigates a simple yet unconventional…

Statistical methods protecting sensitive information or the identity of the data owner have become critical to ensure privacy of individuals as well as of organizations. This paper investigates anonymization methods based on representation…

Large language models (LLMs) have demonstrated exceptional capabilities in text understanding and generation, and they are increasingly being utilized across various domains to enhance productivity. However, due to the high costs of…

A rapidly growing number of applications rely on a small set of closed-source language models (LMs). This dependency might introduce novel security risks if LMs develop self-recognition capabilities. Inspired by human identity verification…

Prompt injection attacks are an emerging threat to large language models (LLMs), enabling malicious users to manipulate outputs through carefully designed inputs. Existing detection approaches often require centralizing prompt data,…

With the rise of personalized, persistent LLM agent frameworks such as OpenClaw, human-centered agentic social networks in which teams of collaborative AI agents serve individual users in a social network across multiple domains are…

While de-identification models can help conceal the identity of the individuals mentioned in a document, they fail to address linkage risks, defined as the potential to map the de-identified text back to its source. One straightforward way…

Addressing contextual privacy concerns remains challenging in interactive settings where large language models (LLMs) process information from multiple sources (e.g., summarizing meetings with private and public information). We introduce a…

Numerous companies have started offering services based on large language models (LLM), such as ChatGPT, which inevitably raises privacy concerns as users' prompts are exposed to the model provider. Previous research on secure reasoning…

Qualitative research often contains personal, contextual, and organizational details that pose privacy risks if not handled appropriately. Manual anonymization is time-consuming, inconsistent, and frequently omits critical identifiers.…

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…

The inference process of modern large language models (LLMs) demands prohibitive computational resources, rendering them infeasible for deployment on consumer-grade devices. To address this limitation, recent studies propose distributed LLM…

Adapting Large Language Models (LLMs) to specific tasks introduces concerns about computational efficiency, prompting an exploration of efficient methods such as In-Context Learning (ICL). However, the vulnerability of ICL to privacy…

The increasing use of machine learning (ML) for Just-In-Time (JIT) defect prediction raises concerns about privacy leakage from software analytics data. Existing anonymization methods, such as tabular transformations and graph…

User identity linkage is a task of recognizing the identities of the same user across different social networks (SN). Previous works tackle this problem via estimating the pairwise similarity between identities from different SN, predicting…

The large language model (LLM) powered recommendation paradigm has been proposed to address the limitations of traditional recommender systems, which often struggle to handle cold start users or items with new IDs. Despite its…

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…