Related papers: Detecting Voice Cloning Attacks via Timbre Waterma…

As large language models (LLMs) become integral to applications such as question answering and content creation, reliable content attribution has become increasingly important. Watermarking is a promising approach, but most existing methods…

Multi-bit watermarking has emerged as a promising solution for embedding imperceptible binary messages into Large Language Model (LLM)-generated text, enabling reliable attribution and tracing of malicious usage of LLMs. Despite recent…

Zero-shot voice conversion (VC) synthesizes speech in a target speaker's voice while preserving linguistic and paralinguistic content. However, timbre leakage-where source speaker traits persist-remains a challenge, especially in neural…

The widely adopted and powerful generative large language models (LLMs) have raised concerns about intellectual property rights violations and the spread of machine-generated misinformation. Watermarking serves as a promising approch to…

We study how to watermark LLM outputs, i.e. embedding algorithmically detectable signals into LLM-generated text to track misuse. Unlike the current mainstream methods that work with a fixed LLM, we expand the watermark design space by…

The expansion of the open source community and the rise of large language models have raised ethical and security concerns on the distribution of source code, such as misconduct on copyrighted code, distributions without proper licenses, or…

Digital watermarking is a promising solution for mitigating some of the risks arising from the misuse of automatically generated text. These approaches either embed non-specific watermarks to allow for the detection of any text generated by…

Watermarking the initial noise of diffusion models has emerged as a promising approach for image provenance, but content-independent noise patterns can be forged via inversion and regeneration attacks. Recent semantic-aware watermarking…

Internet is one of the most valuable resources for information communication and retrievals. Most multimedia signals today are in digital formats. The digital data can be duplicated and edited with great ease which has led to a need for…

In this paper, we investigate the recent state-of-the-art schemes for watermarking large language models (LLMs) outputs. These techniques are claimed to be robust, scalable and production-grade, aimed at promoting responsible usage of LLMs.…

Speech provenance goes beyond detecting whether a watermark is present. Real workflows involve splicing, quoting, trimming, and platform-level transforms that may preserve some regions while altering others. Neural watermarking systems have…

The advancement of Large Language Models (LLMs) has led to increasing concerns about the misuse of AI-generated text, and watermarking for LLM-generated text has emerged as a potential solution. However, it is challenging to generate…

Watermarking of large language models (LLMs) generation embeds an imperceptible statistical pattern within texts, making it algorithmically detectable. Watermarking is a promising method for addressing potential harm and biases from LLMs,…

Large language models (LLMs) can be trained or fine-tuned on data obtained without the owner's consent. Verifying whether a specific LLM was trained on particular data instances or an entire dataset is extremely challenging. Dataset…

Watermarking is the process of embedding information into an image that can survive under distortions, while requiring the encoded image to have little or no perceptual difference from the original image. Recently, deep learning-based…

Recent advances in vision-language pre-trained models (VLPs) have significantly increased visual understanding and cross-modal analysis capabilities. Companies have emerged to provide multi-modal Embedding as a Service (EaaS) based on VLPs…

Backdoor attack aims to deceive a victim model when facing backdoor instances while maintaining its performance on benign data. Current methods use manual patterns or special perturbations as triggers, while they often overlook the…

Machine learning (ML) models are applied in an increasing variety of domains. The availability of large amounts of data and computational resources encourages the development of ever more complex and valuable models. These models are…

The development of large language models (LLMs) has raised concerns about potential misuse. One practical solution is to embed a watermark in the text, allowing ownership verification through watermark extraction. Existing methods primarily…

Large Language Models (LLMs) have demonstrated remarkable capabilities of generating texts resembling human language. However, they can be misused by criminals to create deceptive content, such as fake news and phishing emails, which raises…