Media forensics and deepfakes: an overview
L Verdoliva - IEEE journal of selected topics in signal …, 2020 - ieeexplore.ieee.org
With the rapid progress in recent years, techniques that generate and manipulate
multimedia content can now provide a very advanced level of realism. The boundary …
multimedia content can now provide a very advanced level of realism. The boundary …
Comprehensive survey of image steganography: Techniques, Evaluations, and trends in future research
Storing and communicating secret and/or private information has become part of our daily
life whether it is for our employment or personal well-being. Therefore, secure storage and …
life whether it is for our employment or personal well-being. Therefore, secure storage and …
The stable signature: Rooting watermarks in latent diffusion models
Generative image modeling enables a wide range of applications but raises ethical
concerns about responsible deployment. This paper introduces an active strategy combining …
concerns about responsible deployment. This paper introduces an active strategy combining …
The science of detecting llm-generated text
ACM: Digital Library: Communications of the ACM ACM Digital Library Communications of the
ACM Volume 67, Number 4 (2024), Pages 50-59 The Science of Detecting LLM-Generated Text …
ACM Volume 67, Number 4 (2024), Pages 50-59 The Science of Detecting LLM-Generated Text …
Protecting intellectual property of deep neural networks with watermarking
Deep learning technologies, which are the key components of state-of-the-art Artificial
Intelligence (AI) services, have shown great success in providing human-level capabilities …
Intelligence (AI) services, have shown great success in providing human-level capabilities …
Tree-rings watermarks: Invisible fingerprints for diffusion images
Watermarking the outputs of generative models is a crucial technique for tracing copyright
and preventing potential harm from AI-generated content. In this paper, we introduce a novel …
and preventing potential harm from AI-generated content. In this paper, we introduce a novel …
Stegastamp: Invisible hyperlinks in physical photographs
Printed and digitally displayed photos have the ability to hide imperceptible digital data that
can be accessed through internet-connected imaging systems. Another way to think about …
can be accessed through internet-connected imaging systems. Another way to think about …
Invisible backdoor attacks on deep neural networks via steganography and regularization
Deep neural networks (DNNs) have been proven vulnerable to backdoor attacks, where
hidden features (patterns) trained to a normal model, which is only activated by some …
hidden features (patterns) trained to a normal model, which is only activated by some …
Unbiased watermark for large language models
The recent advancements in large language models (LLMs) have sparked a growing
apprehension regarding the potential misuse. One approach to mitigating this risk is to …
apprehension regarding the potential misuse. One approach to mitigating this risk is to …
Embedding watermarks into deep neural networks
Significant progress has been made with deep neural networks recently. Sharing trained
models of deep neural networks has been a very important in the rapid progress of research …
models of deep neural networks has been a very important in the rapid progress of research …