Related papers: Protecting Language Generation Models via Invisibl…

Self-supervised learning is an emerging machine learning paradigm. Compared to supervised learning which leverages high-quality labeled datasets, self-supervised learning relies on unlabeled datasets to pre-train powerful encoders which can…

Recently, Generative Diffusion Models (GDMs) have showcased their remarkable capabilities in learning and generating images. A large community of GDMs has naturally emerged, further promoting the diversified applications of GDMs in various…

Components of machine learning systems are not (yet) perceived as security hotspots. Secure coding practices, such as ensuring that no execution paths depend on confidential inputs, have not yet been adopted by ML developers. We initiate…

Diffusion-based speech generation has achieved remarkable fidelity, increasing the risk of misuse and unauthorized redistribution. However, most existing generative speech watermarking methods are developed for GAN-based pipelines, and…

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

A deep neural network (DNN) classifier represents a model owner's intellectual property as training a DNN classifier often requires lots of resource. Watermarking was recently proposed to protect the intellectual property of DNN…

The widespread adoption of Retrieval-Augmented Image Generation (RAIG) has raised significant concerns about the unauthorized use of private image datasets. While these systems have shown remarkable capabilities in enhancing generation…

Watermarking generative content serves as a vital tool for authentication, ownership protection, and mitigation of potential misuse. Existing watermarking methods face the challenge of balancing robustness and concealment. They empirically…

With Internet users constantly leaving a trail of text, whether through blogs, emails, or social media posts, the ability to write and protest anonymously is being eroded because artificial intelligence, when given a sample of previous…

A well-trained DNN model can be regarded as an intellectual property (IP) of the model owner. To date, many DNN IP protection methods have been proposed, but most of them are watermarking based verification methods where model owners can…

Large Language Models (LLMs) represent substantial intellectual and economic investments, yet their effectiveness can inadvertently facilitate model imitation via knowledge distillation (KD). In practical scenarios, competitors can distill…

As AI-generated sensitive images become more prevalent, identifying their source is crucial for distinguishing them from real images. Conventional image watermarking methods are vulnerable to common transformations like filters, lossy…

Diffusion models generate high-quality images but pose serious risks like copyright violation and disinformation. Watermarking is a key defense for tracing and authenticating AI-generated content. However, existing methods rely on…

Recent advancements in watermarking techniques have enabled the embedding of secret messages into AI-generated text (AIGT), serving as an important mechanism for AIGT detection. Existing methods typically interfere with the generation…

Google's SynthID-Text, the first ever production-ready generative watermark system for large language model, designs a novel Tournament-based method that achieves the state-of-the-art detectability for identifying AI-generated texts. The…

The rapid adoption of large language models (LLMs), such as GPT-4 and Claude 3.5, underscores the need to distinguish LLM-generated text from human-written content to mitigate the spread of misinformation and misuse in education. One…

Deep neural networks (DNNs) have achieved significant success in real-world applications. However, safeguarding their intellectual property (IP) remains extremely challenging. Existing DNN watermarking for IP protection often require…

Latent Diffusion Models (LDMs) have established themselves as powerful tools in the rapidly evolving field of image generation, capable of producing highly realistic images. However, their widespread adoption raises critical concerns about…

Generative models, especially text-to-image diffusion models, have significantly advanced in their ability to generate images, benefiting from enhanced architectures, increased computational power, and large-scale datasets. While the…

While many deep learning models trained on private datasets have been deployed in various practical tasks, they may pose a privacy leakage risk as attackers could recover informative data or label knowledge from models. In this work, we…