Editguard: Versatile image watermarking for tamper localization and copyright protection
In the era of AI-generated content (AIGC) malicious tampering poses imminent threats to
copyright integrity and information security. Current deep image watermarking while widely …
copyright integrity and information security. Current deep image watermarking while widely …
Sepmark: Deep separable watermarking for unified source tracing and deepfake detection
Malicious Deepfakes have led to a sharp conflict over distinguishing between genuine and
forged faces. Although many countermeasures have been developed to detect Deepfakes …
forged faces. Although many countermeasures have been developed to detect Deepfakes …
V2A-Mark: Versatile Deep Visual-Audio Watermarking for Manipulation Localization and Copyright Protection
AI-generated video has revolutionized short video production, filmmaking, and personalized
media, making video local editing an essential tool. However, this progress also blurs the …
media, making video local editing an essential tool. However, this progress also blurs the …
Investigating Deep Watermark Security: An Adversarial Transferability Perspective
B Qi, J Gao, Y Luo, J Liu, L Wu, B Zhou - arXiv preprint arXiv:2402.16397, 2024 - arxiv.org
The rise of generative neural networks has triggered an increased demand for intellectual
property (IP) protection in generated content. Deep watermarking techniques, recognized for …
property (IP) protection in generated content. Deep watermarking techniques, recognized for …
PiGW: A Plug-in Generative Watermarking Framework
Integrating watermarks into generative images is a critical strategy for protecting intellectual
property and enhancing artificial intelligence security. This paper proposes Plug-in …
property and enhancing artificial intelligence security. This paper proposes Plug-in …
Lossless image steganography: Regard steganography as super-resolution
Image steganography attempts to imperceptibly hide the secret image within the cover
image. Most of the existing deep learning-based steganography approaches have excelled …
image. Most of the existing deep learning-based steganography approaches have excelled …
Image sterilization via overwriting
M Tan, D Guo, L Huang, Z Gu, X Wang, H Zheng - Information Sciences, 2024 - Elsevier
Sterilization refers to the method of removing hidden information from images, effectively
eradicating malicious data embedded within digital media. Existing methods are hampered …
eradicating malicious data embedded within digital media. Existing methods are hampered …
Robust watermarking against arbitrary scaling and cropping attacks
S Wu, W Lu, X Yin, R Yang - Signal Processing, 2025 - Elsevier
Digital watermarking technology has wide application prospects due to its excellent
performance in copyright protection and traceability. However, there are still some gaps in …
performance in copyright protection and traceability. However, there are still some gaps in …
{ChainPatrol}: Balancing Attack Detection and Classification with Performance Overhead for Service Function Chains Using Virtual Trailers
Network functions virtualization enables tenants to outsource their service function chains
(SFCs) to third-party clouds for better agility and cost-effectiveness. However, outsourcing …
(SFCs) to third-party clouds for better agility and cost-effectiveness. However, outsourcing …
Towards robust image watermarking via random distortion assignment based meta-learning
S Zhou, P He, J Liu, J Luo - Journal of Visual Communication and Image …, 2024 - Elsevier
Recently, deep learning-based image watermarking methods have been proposed for
copyright protection, which are robust to common post-processing operations. However …
copyright protection, which are robust to common post-processing operations. However …