Related papers: Staining and locking computer vision models withou…
The commercialization of deep learning creates a compelling need for intellectual property (IP) protection. Deep neural network (DNN) watermarking has been proposed as a promising tool to help model owners prove ownership and fight piracy.…
Deep convolutional neural networks have made outstanding contributions in many fields such as computer vision in the past few years and many researchers published well-trained network for downloading. But recent studies have shown serious…
With the advancement of intelligent healthcare, medical pre-trained language models (Med-PLMs) have emerged and demonstrated significant effectiveness in downstream medical tasks. While these models are valuable assets, they are vulnerable…
Backdoor attacks compromise the integrity and reliability of machine learning models by embedding a hidden trigger during the training process, which can later be activated to cause unintended misbehavior. We propose a novel backdoor…
In the era of costly pre-training of large language models, ensuring the intellectual property rights of model owners, and insuring that said models are responsibly deployed, is becoming increasingly important. To this end, we propose model…
Model merging is a technique that combines multiple finetuned models into a single model without additional training, allowing a free-rider to cheaply inherit specialized capabilities. This study investigates methodologies to suppress…
Motivated by the problem of detecting AI-generated text, we consider the problem of watermarking the output of language models with provable guarantees. We aim for watermarks which satisfy: (a) undetectability, a cryptographic notion…
Obtaining the state of the art performance of deep learning models imposes a high cost to model generators, due to the tedious data preparation and the substantial processing requirements. To protect the model from unauthorized…
The proliferation of deepfake faces poses huge potential negative impacts on our daily lives. Despite substantial advancements in deepfake detection over these years, the generalizability of existing methods against forgeries from unseen…
The state of the art performance of deep learning models comes at a high cost for companies and institutions, due to the tedious data collection and the heavy processing requirements. Recently, [35, 22] proposed to watermark convolutional…
Invisible image watermarking can protect image ownership and prevent malicious misuse of visual generative models. However, existing generative watermarking methods are mainly designed for diffusion models while watermarking for…
Robust invisible watermarking aims to embed hidden information into images such that the watermark can survive various image manipulations. However, the rise of powerful diffusion-based image generation and editing techniques poses a new…
Modern machine learning (ML) models are expensive IP and business competitiveness often depends on keeping this IP confidential. This in turn restricts how these models are deployed; for example, it is unclear how to deploy a model…
It is crucial to protect the intellectual property rights of DNN models prior to their deployment. The DNN should perform two main tasks: its primary task and watermarking task. This paper proposes a lightweight, reliable, and secure DNN…
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…
The rapid advancement of large language models (LLMs) has raised concerns regarding their potential misuse, particularly in generating fake news and misinformation. To address these risks, watermarking techniques for autoregressive language…
Large language models (LLMs) are pre-trained and post-trained on vast amounts of loosely curated data, raising the possibility that these models may have been trained on proprietary datasets or the same benchmarks used for evaluation. This…
Training deep neural networks from scratch could be computationally expensive and requires a lot of training data. Recent work has explored different watermarking techniques to protect the pre-trained deep neural networks from potential…
Embedding watermarks into the output of generative models is essential for establishing copyright and verifiable ownership over the generated content. Emerging diffusion model watermarking methods either embed watermarks in the frequency…
Watermarking has recently emerged as an effective strategy for detecting the outputs of large language models (LLMs). Most existing schemes require white-box access to the model's next-token probability distribution, which is typically not…