VoiceMark: Zero-Shot Voice Cloning-Resistant Watermarking Approach Leveraging Speaker-Specific Latents

Voice cloning VC-resistant watermarking is an emerging technique for tracing and preventing unauthorized cloning. Existing methods effectively trace traditional VC models by training them on watermarked audio but fail in zero-shot VC scenarios, where models synthesize audio from an audio prompt...

MUSE: Model-Agnostic Tabular Watermarking Via Multi-Sample Selection

We introduce MUSE, a watermarking algorithm for tabular generative models. Previous approaches typically leverage DDIM invertibility to watermark tabular diffusion models, but tabular diffusion models exhibit significantly poorer invertibility compared to other modalities, compromising performanc...

VideoMarkBench: Benchmarking Robustness of Video Watermarking

The rapid development of video generative models has led to a surge in highly realistic synthetic videos, raising ethical concerns related to disinformation and copyright infringement. Recently, video watermarking has been proposed as a mitigation strategy by embedding invisible marks into...

CVE-2024-1994

The Image Watermark plugin for WordPress is vulnerable to unauthorized modification of data due to a missing capability check on the watermarkactionajax function in all versions up to, and including, 1.7.3. This makes it possible for authenticated attackers, with subscriber-level access and above...

CVE-2023-28550

Memory corruption in MPP performance while accessing DSM watermark using external memory address...

CVE-2022-0989

An unprivileged user could use the functionality of the NS WooCommerce Watermark WordPress plugin through 2.11.3 to load images that hide malware for example from passing malicious domains to hide their trace, by making them pass through the vulnerable domain...

CVE-2021-32748

Nextcloud Richdocuments in an open source self hosted online office. Nextcloud uses the WOPI "Web Application Open Platform Interface" protocol to communicate with the Collabora Editor, the communication between these two services was not protected by a credentials or IP check. Whilst this does n...

Training-Free Watermarking for Autoregressive Image Generation

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 autoregressive image generation models remains largely underexplored...

Traceable Black-Box Watermarks for Federated Learning

Whitepaper called Traceable Black-Box Watermarks For Federated Learning...

LLM-Text Watermarking Based on Lagrange Interpolation

The rapid advancement of LLMs Large Language Models has established them as a foundational technology for many AI and ML-powered human computer interactions. A critical challenge in this context is the attribution of LLM-generated text -- either to the specific language model that produced it or ...

Towards Dataset Copyright Evasion Attack against Personalized Text-To-Image Diffusion Models

Text-to-image T2I diffusion models have rapidly advanced, enabling high-quality image generation conditioned on textual prompts. However, the growing trend of fine-tuning pre-trained models for personalization raises serious concerns about unauthorized dataset usage. To combat this, dataset...

VIDSTAMP: a Temporally-Aware Watermark for Ownership and Integrity in Video Diffusion Models

The rapid rise of video diffusion models has enabled the generation of highly realistic and temporally coherent videos, raising critical concerns about content authenticity, provenance, and misuse. Existing watermarking approaches, whether passive, post-hoc, or adapted from image-based techniques...

Watermark Overwriting Attack on StegaStamp Algorithm

This paper presents an attack method on the StegaStamp watermarking algorithm that completely removes watermarks from an image with minimal quality loss, developed as part of the NeurIPS "Erasing the invisible" competition...

CVE-2025-29316

An issue in DataPatrol Screenshot watermark, printing watermark agent v.3.5.2.0 allows a physically proximate attacker to obtain sensitive information. NOTE: the Supplier disputes the Print Job Watermark Bypass claim because the watermark is added by hooking into the OS printing mechanism, and th...

Cluster-Aware Attacks on Graph Watermarks

Data from domains such as social networks, healthcare, finance, and cybersecurity can be represented as graph-structured information. Given the sensitive nature of this data and their frequent distribution among collaborators, ensuring secure and attributable sharing is essential. Graph...

PT-Mark: Invisible Watermarking for Text-To-Image Diffusion Models Via Semantic-Aware Pivotal Tuning

Watermarking for diffusion images has drawn considerable attention due to the widespread use of text-to-image diffusion models and the increasing need for their copyright protection. Recently, advanced watermarking techniques, such as Tree Ring, integrate watermarks by embedding traceable pattern...

CVE-2025-29316

An issue in DataPatrol Screenshot watermark, printing watermark agent v.3.5.2.0 allows a physically proximate attacker to obtain sensitive information. NOTE: the Supplier disputes the Print Job Watermark Bypass claim because the watermark is added by hooking into the OS printing mechanism, and th...

CVE-2025-29316

An issue in DataPatrol Screenshot watermark, printing watermark agent v.3.5.2.0 allows a physically proximate attacker to obtain sensitive information. NOTE: the Supplier disputes the Print Job Watermark Bypass claim because the watermark is added by hooking into the OS printing mechanism, and th...

PT-2025-17227 · Unknown · Datapatrol Screenshot Watermark

Name of the Vulnerable Software and Affected Versions: DataPatrol Screenshot watermark, printing watermark agent version 3.5.2.0 Description: An issue in the software allows a physically proximate attacker to obtain sensitive information. Recommendations: For version 3.5.2.0, at the moment, there...

CVE-2025-21874

In the Linux kernel, the following vulnerability has been resolved: dm-integrity: Avoid divide by zero in table status in Inline mode In Inline mode, the journal is unused, and journalsectors is zero. Calculating the journal watermark requires dividing by journalsectors, which should be done only...