Related papers: Excuse me, sir? Your language model is leaking (in…

Large language models (LLMs) are increasingly used in high-stakes settings, where overconfident responses can mislead users. Reliable confidence estimation has been shown to enhance trust and task accuracy. Yet existing methods face…

Most LLM fingerprinting methods teach the model to respond to a few fixed queries with predefined atypical responses (keys). This memorization often does not survive common deployment steps such as finetuning or quantization, and such keys…

Substantial research works have shown that deep models, e.g., pre-trained models, on the large corpus can learn universal language representations, which are beneficial for downstream NLP tasks. However, these powerful models are also…

Language Models (LMs) may acquire harmful knowledge, and yet feign ignorance of these topics when under audit. Inspired by the recent discovery of deception-related behaviour patterns in LMs, we aim to train classifiers that detect when a…

A meaningful text can be hidden inside another, completely different yet still coherent and plausible, text of the same length. For example, a tweet containing a harsh political critique could be embedded in a tweet that celebrates the same…

Large Language Models (LLMs) are increasingly used to generate dynamic dialogue for game NPCs. However, their integration raises new security concerns. In this study, we examine whether adversarial prompt injection can cause LLM-based NPCs…

The rapid spread of text generated by large language models (LLMs) makes it increasingly difficult to distinguish authentic human writing from machine output. Watermarking offers a promising solution: model owners can embed an imperceptible…

The recent explosion of high-quality language models has necessitated new methods for identifying AI-generated text. Watermarking is a leading solution and could prove to be an essential tool in the age of generative AI. Existing approaches…

Large Language Models (LLMs) represent a significant advancement in artificial intelligence, finding applications across various domains. However, their reliance on massive internet-sourced datasets for training brings notable privacy…

The interactive nature of Large Language Models (LLMs), which closely track user data and context, has prompted users to share personal and private information in unprecedented ways. Even when users opt out of allowing their data to be used…

Large language models (LLMs) have demonstrated impressive capabilities in natural language processing. However, their internal mechanisms are still unclear and this lack of transparency poses unwanted risks for downstream applications.…

Watermarking has emerged as a promising way to detect LLM-generated text, by augmenting LLM generations with later detectable signals. Recent work has proposed multiple families of watermarking schemes, several of which focus on preserving…

Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models (LMs). However, the robustness of the watermarking schemes has not been…

Recent advances in Large Language Models (LLMs) have raised urgent concerns about LLM-generated text authenticity, prompting regulatory demands for reliable identification mechanisms. Although watermarking offers a promising solution,…

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…

Watermarking schemes for large language models (LLMs) have been proposed to identify the source of the generated text, mitigating the potential threats emerged from model theft. However, current watermarking solutions hardly resolve the…

We study secret elicitation: discovering knowledge that an AI possesses but does not explicitly verbalize. As a testbed, we train three families of large language models (LLMs) to possess specific knowledge that they apply downstream but…

We consider the emerging problem of identifying the presence and use of watermarking schemes in widely used, publicly hosted, closed source large language models (LLMs). We introduce a suite of baseline algorithms for identifying watermarks…

Large Language Models (LLMs) have demonstrated extraordinary capabilities and contributed to multiple fields, such as generating and summarizing text, language translation, and question-answering. Nowadays, LLM is becoming a very popular…

Recently, the powerful large language models (LLMs) have been instrumental in propelling the progress of recommender systems (RS). However, while these systems have flourished, their susceptibility to security threats has been largely…