相关论文: Discovering Universal Activation Directions for PI…

Language model inversion seeks to recover hidden prompts using only language model outputs. This capability has implications for security and accountability in language model deployments, such as leaking private information from an…

The advancement of large language models (LLMs) brings notable improvements across various applications, while simultaneously raising concerns about potential private data exposure. One notable capability of LLMs is their ability to form…

Large Language Models (LLMs) have a privacy concern because they memorize training data (including personally identifiable information (PII) like emails and phone numbers) and leak it during inference. A company can train an LLM on its…

In-Context Learning (ICL) has become a standard technique for adapting Large Language Models (LLMs) to specialized tasks by supplying task-specific exemplars within the prompt. However, when these exemplars contain sensitive information,…

Redacting Personally Identifiable Information (PII) from unstructured text is critical for ensuring data privacy in regulated domains. While earlier approaches have relied on rule-based systems and domain-specific Named Entity Recognition…

Large Language Models (LLMs) memorize, and thus, among huge amounts of uncontrolled data, may memorize Personally Identifiable Information (PII), which should not be stored and, consequently, not leaked. In this paper, we introduce Private…

Large Language Models (LLMs) show remarkable potential for few-shot information extraction (IE), yet their performance is highly sensitive to the choice of in-context examples. Conventional selection strategies often fail to provide…

Large Language Models (LLMs) generate responses based on user prompts. Often, these prompts may contain highly sensitive information, including personally identifiable information (PII), which could be exposed to third parties hosting these…

As Large Language Model (LLM) agents become more capable, their coordinated use in the form of multi-agent systems is anticipated to emerge as a practical paradigm. Prior work has examined the safety and misuse risks associated with agents.…

With the rise of large language models (LLMs), increasing research has recognized their risk of leaking personally identifiable information (PII) under malicious attacks. Although efforts have been made to protect PII in LLMs, existing…

An unintended consequence of the vast pretraining of Large Language Models (LLMs) is the verbatim memorization of fragments of their training data, which may contain sensitive or copyrighted information. In recent years, unlearning has…

Activation-based control steers large language models (LLMs) by intervening on their internal representations during inference, and has emerged as an effective paradigm for controlling behaviors such as persona and style. However, existing…

Due to the sensitive nature of personally identifiable information (PII), its owners may have the authority to control its inclusion or request its removal from large-language model (LLM) training. Beyond this, PII may be added or removed…

Large Language Models (LLMs) enable a new ecosystem with many downstream applications, called LLM applications, with different natural language processing tasks. The functionality and performance of an LLM application highly depend on its…

The deployment of Large Language Models in agentic, multi-turn conversational settings has introduced a class of privacy vulnerabilities that existing protection mechanisms are not designed to address. Current approaches to Personally…

Building natural language inference (NLI) benchmarks that are both challenging for modern techniques, and free from shortcut biases is difficult. Chief among these biases is "single sentence label leakage," where annotator-introduced…

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…

Prompt serves as a crucial link in interacting with large language models (LLMs), widely impacting the accuracy and interpretability of model outputs. However, acquiring accurate and high-quality responses necessitates precise prompts,…

Large language models (LLMs) have transformed natural language processing, but their ability to memorize training data poses significant privacy risks. This paper investigates model inversion attacks on the Llama 3.2 model, a multilingual…

Vision Language Models (VLMs) are increasingly integrated into privacy-critical domains, yet existing evaluations of personally identifiable information (PII) leakage largely treat privacy as a static extraction task and ignore how a…