Related papers: Invisible Flow Watermarks for Channels with Depend…
We study multi-bit watermarking for data generated by stochastic processes, where a hidden message is embedded during sampling and must be decodable by an authorized detector that possesses side information unavailable to unauthorized…
In order to protect the intellectual property (IP) of deep neural networks (DNNs), many existing DNN watermarking techniques either embed watermarks directly into the DNN parameters or insert backdoor watermarks by fine-tuning the DNN…
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,…
Linking network flows is an important problem in intrusion detection as well as anonymity. Passive traffic analysis can link flows but requires long periods of observation to reduce errors. Active traffic analysis, also known as flow…
Watermark has been widely deployed by industry to detect AI-generated images. The robustness of such watermark-based detector against evasion attacks in the white-box and black-box settings is well understood in the literature. However, the…
We present a novel technique for modulating the appearance frequency of a few tokens within a dataset for encoding an invisible watermark that can be used to protect ownership rights upon data. We develop optimal as well as fast heuristic…
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…
Deep learning has been achieving top performance in many tasks. Since training of a deep learning model requires a great deal of cost, we need to treat neural network models as valuable intellectual properties. One concern in such a…
Robust invisible watermarking schemes aim to embed hidden information into images such that the watermark survives common manipulations. However, powerful diffusion-based image generation and editing techniques now pose a new threat to…
Digital watermarking is extensively used in ownership authentication and copyright protection. In this paper, we propose an efficient thresholding scheme to improve the watermark embedding procedure in an image. For the proposed algorithm,…
Rapid advancements in video diffusion models have enabled the creation of realistic videos, raising concerns about unauthorized use and driving the demand for techniques to protect model ownership. Existing watermarking methods, while…
Recent advances in generative AI have enabled the creation of highly realistic digital content, raising concerns around authenticity, ownership, and misuse. While watermarking has become an increasingly important mechanism to trace and…
Hardware acceleration in modern networks creates monitoring blind spots by offloading flows to a non-observable state, hindering real-time service degradation (SD) detection. To address this, we propose and formalize a novel inter-flow…
Deep learning based blind watermarking works have gradually emerged and achieved impressive performance. However, previous deep watermarking studies mainly focus on fixed low-resolution images while paying less attention to arbitrary…
In this work, we address the liability issues that may arise due to unauthorized sharing of personal data. We consider a scenario in which an individual shares his sequential data (such as genomic data or location patterns) with several…
Multiple watermarking technique, embedding several watermarks in one carrier, has enabled many interesting applications. In this study, a novel multiple watermarking algorithm is proposed based on the spirit of spread transform dither…
Safeguarding the intellectual property of machine learning models has emerged as a pressing concern in AI security. Model watermarking is a powerful technique for protecting ownership of machine learning models, yet its reliability has been…
Latent Diffusion Models (LDMs) enable a wide range of applications but raise ethical concerns regarding illegal utilization. Adding watermarks to generative model outputs is a vital technique employed for copyright tracking and mitigating…
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…
Watermarking enables GenAI providers to verify whether content was generated by their models. A watermark is a hidden signal in the content, whose presence can be detected using a secret watermark key. A core security threat are forgery…