Related papers: RAT-Bench: A Comprehensive Benchmark for Text Anon…

In the digital era, with escalating privacy concerns, it's imperative to devise robust strategies that protect private data while maintaining the intrinsic value of textual information. This research embarks on a comprehensive examination…

The rapid advancement of large language models (LLMs) has enabled powerful authorship inference capabilities, raising growing concerns about unintended deanonymization risks in textual data such as news articles. In this work, we introduce…

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…

Large Language Models (LLMs) perform impressively well in various applications. However, the potential for misuse of these models in activities such as plagiarism, generating fake news, and spamming has raised concern about their…

Large Language Models (LLMs) can generate human-like disinformation, yet their ability to personalise such content across languages and demographics remains underexplored. This study presents the first large-scale, multilingual analysis of…

This study introduces a prescriptive annotation benchmark grounded in humanities research to ensure consistent, unbiased labeling of offensive language, particularly for casual and non-mainstream language uses. We contribute two newly…

Considerable research efforts have been devoted to ensuring that large language models (LLMs) align with human values and generate safe text. However, an excessive focus on sensitivity to certain topics can compromise the model's robustness…

Recently, powerful Large Language Models (LLMs) have become easily accessible to hundreds of millions of users world-wide. However, their strong capabilities and vast world knowledge do not come without associated privacy risks. In this…

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.…

When building Large Language Models (LLMs), it is paramount to bear safety in mind and protect them with guardrails. Indeed, LLMs should never generate content promoting or normalizing harmful, illegal, or unethical behavior that may…

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,…

The increasing use of Artificial Intelligence (AI) technologies, such as Large Language Models (LLMs) has led to nontrivial improvements in various tasks, including accurate authorship identification of documents. However, while LLMs…

Text anomaly detection is a critical task in natural language processing (NLP), with applications spanning fraud detection, misinformation identification, spam detection and content moderation, etc. Despite significant advances in large…

Recent advancements in Large Language Models (LLMs) have demonstrated significant progress in various areas, such as text generation and code synthesis. However, the reliability of performance evaluation has come under scrutiny due to data…

Sanitizing sensitive text data typically involves removing personally identifiable information (PII) or generating synthetic data under the assumption that these methods adequately protect privacy; however, their effectiveness is often only…

We present REMARK-LLM, a novel efficient, and robust watermarking framework designed for texts generated by large language models (LLMs). Synthesizing human-like content using LLMs necessitates vast computational resources and extensive…

Large language models (LLMs) are vulnerable when trained on datasets containing harmful content, which leads to potential jailbreaking attacks in two scenarios: the integration of harmful texts within crowdsourced data used for pre-training…

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…

Public leaderboards increasingly suggest that large language models (LLMs) surpass human experts on benchmarks spanning academic knowledge, law, and programming. Yet most benchmarks are fully public, their questions widely mirrored across…

Interactions with online Large Language Models raise privacy issues where providers can gather sensitive information about users and their companies from the prompts. While textual prompts can be sanitized using Differential Privacy, we…