Related papers: Watermarking Language Models with Error Correcting…

Deep learning techniques are one of the most significant elements of any Artificial Intelligence (AI) services. Recently, these Machine Learning (ML) methods, such as Deep Neural Networks (DNNs), presented exceptional achievement in…

Watermarking is one of the most important copyright protection tools for digital media. The most challenging type of watermarking is the imperceptible one, which embeds identifying information in the data while retaining the latter's…

The rapid development of Large Language Models (LLMs) has intensified concerns about content traceability and potential misuse. Existing watermarking schemes for sampled text often face trade-offs between maintaining text quality and…

Deep neural networks have recently achieved significant progress. Sharing trained models of these deep neural networks is very important in the rapid progress of researching or developing deep neural network systems. At the same time, it is…

Watermarking for large language models (LLMs) offers a promising approach to identifying AI-generated text. Existing approaches, however, either compromise the distribution of original generated text by LLMs or are limited to embedding…

Automatic detection of synthetic speech is becoming increasingly important as current synthesis methods are both near indistinguishable from human speech and widely accessible to the public. Audio watermarking and other active disclosure…

Distinguishing AI-generated code from human-written code is becoming crucial for tasks such as authorship attribution, content tracking, and misuse detection. Based on this, N-gram-based watermarking schemes have emerged as prominent, which…

In this work, we introduce a novel deep learning-based approach to text-in-image watermarking, a method that embeds and extracts textual information within images to enhance data security and integrity. Leveraging the capabilities of deep…

Generative models are now capable of synthesizing images, speeches, and videos that are hardly distinguishable from authentic contents. Such capabilities cause concerns such as malicious impersonation and IP theft. This paper investigates a…

Watermarking generative models consists of planting a statistical signal (watermark) in a model's output so that it can be later verified that the output was generated by the given model. A strong watermarking scheme satisfies the property…

There has been a remarkable increase in the data exchange over web and the widespread use of digital media. As a result, multimedia data transfers also had a boost up. The mounting interest with reference to digital watermarking throughout…

Large language models (LLMs) have significantly enhanced the usability of AI-generated code, providing effective assistance to programmers. This advancement also raises ethical and legal concerns, such as academic dishonesty or the…

Watermarking has become a practical tool for tracing language model outputs, but it modifies token probabilities at inference time, which were carefully tuned by alignment training. This creates a tension: how do watermark-induced shifts…

A generative AI model can generate extremely realistic-looking content, posing growing challenges to the authenticity of information. To address the challenges, watermark has been leveraged to detect AI-generated content. Specifically, a…

This paper introduces RoSeMary, the first-of-its-kind ML/Crypto codesign watermarking framework that regulates LLM-generated code to avoid intellectual property rights violations and inappropriate misuse in software development.…

The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringement. Recently, video watermarking has been proposed as a…

We present a publicly-detectable watermarking scheme for LMs: the detection algorithm contains no secret information, and it is executable by anyone. We embed a publicly-verifiable cryptographic signature into LM output using rejection…

Watermarking combines an imperceptible change to an input image that will trigger a detector, to assert provenance and protect intellectual property. The literature has shown great interest in attacks on watermarking schemes: attackers are…

As policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization…

Text watermarking schemes have gained considerable attention in recent years, yet still face critical challenges in achieving simultaneous robustness, generalizability, and imperceptibility. This paper introduces a new embedding…