Related papers: Provably Robust Multi-bit Watermarking for AI-gene…

With the rapid development of cloud-based services, large language models have become increasingly accessible through various web platforms. However, this accessibility has also led to growing risks of model abuse. LLM watermarking has…

We study watermarking schemes for language models with provable guarantees. As we show, prior works offer no robustness guarantees against adaptive prompting: when a user queries a language model more than once, as even benign users do. And…

The widespread use of Large Language Models (LLMs), celebrated for their ability to generate human-like text, has raised concerns about misinformation and ethical implications. Addressing these concerns necessitates the development of…

Image generation algorithms are increasingly integral to diverse aspects of human society, driven by their practical applications. However, insufficient oversight in artificial Intelligence generated content (AIGC) can facilitate the spread…

Text watermarks for large language models (LLMs) have been commonly used to identify the origins of machine-generated content, which is promising for assessing liability when combating deepfake or harmful content. While existing…

In recent years, LLM watermarking has emerged as an attractive safeguard against AI-generated content, with promising applications in many real-world domains. However, there are growing concerns that the current LLM watermarking schemes are…

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…

The increasing deployment of intelligent agents in digital ecosystems, such as social media platforms, has raised significant concerns about traceability and accountability, particularly in cybersecurity and digital content protection.…

AI-generated images have become so good in recent years that individuals often cannot distinguish them any more from "real" images. This development, combined with the rapid spread of AI-generated content online, creates a series of…

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…

Recent years have witnessed a proliferation of valuable original natural language contents found in subscription-based media outlets, web novel platforms, and outputs of large language models. However, these contents are susceptible to…

We study the problem of multi-bit watermarking for large language models (LLMs). We introduce a block-autoregressive model inspired by multi-token prediction, in which the encoder has limited non-causal access to token distributions within…

Recent advances in LLM watermarking methods such as SynthID-Text by Google DeepMind offer promising solutions for tracing the provenance of AI-generated text. However, our robustness assessment reveals that SynthID-Text is vulnerable to…

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…

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…

With the development of large models, watermarks are increasingly employed to assert copyright, verify authenticity, or monitor content distribution. As applications become more multimodal, the utility of watermarking techniques becomes…

Phishing remains a persistent cybersecurity threat; however, developing scalable and effective user training is labor-intensive and challenging to maintain. Generative Artificial Intelligence offers an interesting opportunity, but empirical…

Efficient knowledge injection methods for Large Language Models (LLMs), such as In-Context Learning, knowledge editing, and efficient parameter fine-tuning, significantly enhance model utility on downstream tasks. However, they also pose…

Watermarking for large language models (LLMs) is a promising approach for detecting LLM-generated text and enabling responsible deployment. However, existing watermarking methods are often vulnerable to semantic-invariant attacks, such as…

Phishing remains a critical cybersecurity threat, especially with the advent of large language models (LLMs) capable of generating highly convincing malicious content. Unlike earlier phishing attempts which are identifiable by grammatical…