Related papers: FakeMark: Deepfake Speech Attribution With Waterma…
As generative AI models produce increasingly realistic output, both academia and industry are focusing on the ability to detect whether an output was generated by an AI model or not. Many of the research efforts and policy discourse are…
LLM watermarks allow tracing AI-generated texts by inserting a detectable signal into their generated content. Recent works have proposed a wide range of watermarking algorithms, each with distinct designs, usually built using a bottom-up…
Watermarking of language model outputs enables statistical detection of model-generated text, which can mitigate harms and misuses of language models. Existing watermarking strategies operate by altering the decoder of an existing language…
Watermarking plays a key role in the provenance and detection of AI-generated content. While existing methods prioritize robustness against real-world distortions (e.g., JPEG compression and noise addition), we reveal a fundamental…
In light of recent advancements in generative AI models, it has become essential to distinguish genuine content from AI-generated one to prevent the malicious usage of fake materials as authentic ones and vice versa. Various techniques have…
Digital image watermarking is the process of embedding and extracting watermark covertly on a carrier image. Incorporating deep learning networks with image watermarking has attracted increasing attention during recent years. However,…
The widespread adoption of large language models (LLMs) necessitates reliable methods to detect LLM-generated text. We introduce SimMark, a robust sentence-level watermarking algorithm that makes LLMs' outputs traceable without requiring…
Data leakage from API responses has drawn wide attention. APIs are often not fully regulated, making them easy to abuse. One common solution is to embed watermarks into API responses for traceability. However, existing watermarking methods…
AI-powered generative models have significantly expanded the possibilities for editing, manipulating, and creating high-quality images. Particularly, images that falsely appear to originate from trusted sources pose a serious threat,…
Speaker anonymization aims to suppress speaker individuality to protect privacy in speech while preserving the other aspects, such as speech content. One effective solution for anonymization is to modify the McAdams coefficient. In this…
The promise of LLM watermarking rests on a core assumption that a specific watermark proves authorship by a specific model. We demonstrate that this assumption is dangerously flawed. We introduce the threat of watermark spoofing, a…
Deepfake audio presents a growing threat to digital security, due to its potential for social engineering, fraud, and identity misuse. However, existing detection models suffer from poor generalization across datasets, due to implicit…
Watermarking is a technique that involves embedding nearly unnoticeable statistical signals within generated content to help trace its source. This work focuses on a scenario where an untrusted third-party user sends prompts to a trusted…
Invisible watermarking for autoregressive (AR) image generation has recently gained attention as a means of protecting image ownership and tracing AI-generated content. However, existing approaches suffer from three key limitations: (1)…
This paper presents the first study on the impact of audio watermarking on spoofing countermeasures. While anti-spoofing systems are essential for securing speech-based applications, the influence of widely used audio watermarking,…
Deep neural networks are playing an important role in many real-life applications. After being trained with abundant data and computing resources, a deep neural network model providing service is endowed with economic value. An important…
Natural language processing (NLP) technology has shown great commercial value in applications such as sentiment analysis. But NLP models are vulnerable to the threat of pirated redistribution, damaging the economic interests of model…
Modern audio is created by mixing stems from different sources, raising the question: can we independently watermark each stem and recover all watermarks after separation? We study a separation-first, multi-stream watermarking…
Watermarking has become a plausible candidate for ownership verification and intellectual property protection of deep neural networks. Regarding image classification neural networks, current watermarking schemes uniformly resort to backdoor…
Watermarking is a crucial tool for safeguarding copyrights and can serve as a more aesthetically pleasing alternative to QR codes. In recent years, watermarking methods based on deep learning have proved superior robustness against complex…