相关论文: GaussMark: A Practical Approach for Structural Wat…

Watermarking has offered an effective approach to distinguishing text generated by large language models (LLMs) from human-written text. However, the pervasive presence of human edits on LLM-generated text dilutes watermark signals, thereby…

The impressive performances of Large Language Models (LLMs) and their immense potential for commercialization have given rise to serious concerns over the Intellectual Property (IP) of their training data. In particular, the synthetic texts…

Watermarking algorithms for Large Language Models (LLMs) effectively identify machine-generated content by embedding and detecting hidden statistical features in text. However, such embedding leads to a decline in text quality, especially…

A recent watermarking scheme for language models achieves distortion-free embedding and robustness to edit-distance attacks. However, it suffers from limited generation diversity and high detection overhead. In parallel, recent research has…

Motivated by the problem of detecting AI-generated text, we consider the problem of watermarking the output of language models with provable guarantees. We aim for watermarks which satisfy: (a) undetectability, a cryptographic notion…

To foster trustworthy Artificial Intelligence (AI) within the European Union, the AI Act requires providers to mark and detect the outputs of their general-purpose models. The Article 50 and Recital 133 call for marking methods that are…

In recent years, tremendous success has been witnessed in Retrieval-Augmented Generation (RAG), widely used to enhance Large Language Models (LLMs) in domain-specific, knowledge-intensive, and privacy-sensitive tasks. However, attackers may…

Watermarking has recently emerged as an effective strategy for detecting the generations of large language models (LLMs). The strength of a watermark typically depends strongly on the entropy afforded by the language model and the set of…

As Large Language Models (LLMs) become increasingly integrated into many technological ecosystems across various domains and industries, identifying which model is deployed or being interacted with is critical for the security and…

The rapid proliferation of generative audio synthesis and editing technologies has raised serious concerns about copyright infringement, data provenance, and the spread of misinformation via deepfake audio. Watermarking offers a proactive…

Natural language generation (NLG) applications have gained great popularity due to the powerful deep learning techniques and large training corpus. The deployed NLG models may be stolen or used without authorization, while watermarking has…

Watermarking techniques offer a promising way to identify machine-generated content via embedding covert information into the contents generated from language models. A challenge in the domain lies in preserving the distribution of original…

Large Language Models (LLMs) have revolutionised the field of Natural Language Processing (NLP) and have achieved state-of-the-art performance in practically every task in this field. However, the prevalent approach used in text generation,…

The rapid growth of Large Language Models (LLMs) has highlighted the pressing need for reliable mechanisms to verify content ownership and ensure traceability. Watermarking offers a promising path forward, but it remains limited by privacy…

In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive models to generative models and autonomous agents, the…

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…

The growing use of large language models (LLMs) for sensitive applications has highlighted the need for effective watermarking techniques to ensure the provenance and accountability of AI-generated text. However, most existing watermarking…

Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to LLM watermarking is to construct a green/red token list and assign higher or lower…

Graph representation learning, involving both node features and graph structures, is crucial for real-world applications but often encounters pervasive noise. State-of-the-art methods typically address noise by focusing separately on node…

The indistinguishability of AI-generated content from human text raises challenges in transparency and accountability. While several methods exist to watermark models behind APIs, embedding watermark strategies directly into model weights…