相关论文: Addressing Tokenization Inconsistency in Steganogr…

The proliferation of AI-generated images has intensified the need for robust content authentication methods. We present InvisMark, a novel watermarking technique designed for high-resolution AI-generated images. Our approach leverages…

Token-inconsistency bugs (TIBs) involve the misuse of syntactically valid yet incorrect code tokens, such as misused variables and erroneous function invocations, which can often lead to software bugs. Unlike simple syntactic bugs, TIBs…

Vision-Language-Action (VLA) models excel in robotic manipulation but suffer from significant inference latency due to processing dense visual tokens. Existing token reduction methods predominantly rely on attention magnitude as a static…

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…

Digital watermarking techniques are crucial for copyright protection and source identification of images, especially in the era of generative AI models. However, many existing watermarking methods, particularly content-agnostic approaches…

The capabilities of large language models have grown significantly in recent years and so too have concerns about their misuse. It is important to be able to distinguish machine-generated text from human-authored content. Prior works have…

With the widespread adoption of Large Language Models (LLMs), concerns about potential misuse have emerged. To this end, watermarking has been adapted to LLM, enabling a simple and effective way to detect and monitor generated text.…

With the increasing use of large language models (LLMs) in daily life, concerns have emerged regarding their potential misuse and societal impact. Watermarking is proposed to trace the usage of specific models by injecting patterns into…

Verifying the authenticity of AI-generated text has become increasingly important with the rapid advancement of large language models, and unbiased watermarking has emerged as a promising approach due to its ability to preserve output…

Generative images have proliferated on Web platforms in social media and online copyright distribution scenarios, and semantic watermarking has increasingly been integrated into diffusion models to support reliable provenance tracking and…

Text watermarking has emerged as a pivotal technique for identifying machine-generated text. However, existing methods often rely on arbitrary vocabulary partitioning during decoding to embed watermarks, which compromises the availability…

In the digital economy era, digital watermarking serves as a critical basis for ownership proof of massive replicable content, including AI-generated and other virtual assets. Designing robust watermarks capable of withstanding various…

Tokenization underlies every large language model, yet it remains an under-theorized and inconsistently designed component. Common subword approaches such as Byte Pair Encoding (BPE) offer scalability but often misalign with linguistic…

Digital watermarks can be embedded into AI-generated content (AIGC) by initializing the generation process with starting points sampled from a secret distribution. When combined with pseudorandom error-correcting codes, such watermarked…

In the present-day scenario, Large Language Models (LLMs) are establishing their presence as powerful instruments permeating various sectors of society. While their utility offers valuable support to individuals, there are multiple concerns…

State-of-the-art text-to-image models generate photorealistic images at an unprecedented speed. This work focuses on models that operate in a bitwise autoregressive manner over a discrete set of tokens that is practically infinite in size.…

The recent advancements in large language models (LLMs) have sparked a growing apprehension regarding the potential misuse. One approach to mitigating this risk is to incorporate watermarking techniques into LLMs, allowing for the tracking…

Watermarking by altering token sampling probabilities based on red-green list is a promising method for tracing the origin of text generated by large language models (LLMs). However, existing watermark methods often struggle with a…

In the rapidly evolving domain of artificial intelligence, safeguarding the intellectual property of Large Language Models (LLMs) is increasingly crucial. Current watermarking techniques against model extraction attacks, which rely on…

Artificial Intelligence (AI) has found wide application, but also poses risks due to unintentional or malicious tampering during deployment. Regular checks are therefore necessary to detect and prevent such risks. Fragile watermarking is a…