Related papers: EmbTracker: Traceable Black-box Watermarking for F…

Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the watermarked text, high detectability, and robustness against…

Deep Neural Networks (DNN) are vulnerable to adversarial perturbations-small changes crafted deliberately on the input to mislead the model for wrong predictions. Adversarial attacks have disastrous consequences for deep learning-empowered…

Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive content, such as fake news and phishing emails, which raises…

We study how to watermark LLM outputs, i.e. embedding algorithmically detectable signals into LLM-generated text to track misuse. Unlike the current mainstream methods that work with a fixed LLM, we expand the watermark design space by…

Large language models (LLMs) can be misused to reveal sensitive information, such as weapon-making instructions or writing malware. LLM providers rely on $\emph{monitoring}$ to detect and flag unsafe behavior during inference. An open…

Large language models (LLMs) have demonstrated outstanding performance, making them valuable digital assets with significant commercial potential. Unfortunately, the LLM and its API are susceptible to intellectual property theft.…

Large language models (LLMs) demonstrate remarkable capabilities across various tasks. However, their deployment introduces significant risks related to intellectual property. In this context, we focus on model stealing attacks, where…

Semantic communication has emerged as a pillar for the next generation of communication systems due to its capabilities in alleviating data redundancy. Most semantic communication systems are built upon advanced deep learning models whose…

Currently, Large Language Models (LLMs) feature a diversified architectural landscape, including traditional Transformer, GateDeltaNet, and Mamba. However, the evolutionary laws of hierarchical representations, task knowledge formation…

Private data, being larger and quality-higher than public data, can greatly improve large language models (LLM). However, due to privacy concerns, this data is often dispersed in multiple silos, making its secure utilization for LLM…

Multilingual watermarking aims to make large language model (LLM) outputs traceable across languages, yet current methods still fall short. Despite claims of cross-lingual robustness, they are evaluated only on high-resource languages. We…

Large language models (LLMs) demonstrate general intelligence across a variety of machine learning tasks, thereby enhancing the commercial value of their intellectual property (IP). To protect this IP, model owners typically allow user…

Self-supervised learning (SSL) encoders are invaluable intellectual property (IP). However, no existing SSL watermarking for IP protection can concurrently satisfy the following two practical requirements: (1) provide ownership verification…

Federated Learning (FL) enables model training across decentralized devices by communicating solely local model updates to an aggregation server. Although such limited data sharing makes FL more secure than centralized approached, FL…

The huge supporting training data on the Internet has been a key factor in the success of deep learning models. However, this abundance of public-available data also raises concerns about the unauthorized exploitation of datasets for…

Despite the growing capabilities of autonomous agents powered by large language models (LLMs), their adoption in high-stakes domains remains limited. A key barrier is security: the inherently nondeterministic behavior of LLM agents defies…

Reliably predicting the behavior of language models -- such as whether their outputs are correct or have been adversarially manipulated -- is a fundamentally challenging task. This is often made even more difficult as frontier language…

Watermarking is a promising defense against the misuse of large language models (LLMs), yet it remains vulnerable to scrubbing and spoofing attacks. This vulnerability stems from an inherent trade-off governed by watermark window size:…

In this paper, we initiate the study of \emph{multi-designated detector watermarking (MDDW)} for large language models (LLMs). This technique allows model providers to generate watermarked outputs from LLMs with two key properties: (i) only…

Model watermarking utilizes internal representations to protect the ownership of large language models (LLMs). However, these features inevitably undergo complex distortions during realistic model modifications such as fine-tuning,…