Video Signature: In-Generation Watermarking for Latent Video Diffusion Models

The rapid development of Artificial Intelligence Generated Content AIGC has led to significant progress in video generation but also raises serious concerns about intellectual property protection and reliable content tracing. Watermarking is a widely adopted solution to this issue, but existing...

Unveiling Impact of Frequency Components on Membership Inference Attacks for Diffusion Models

Diffusion models have achieved tremendous success in image generation, but they also raise significant concerns regarding privacy and copyright issues. Membership Inference Attacks MIAs are designed to ascertain whether specific data were utilized during a model's training phase. As current MIAs...

MixBridge: Heterogeneous Image-To-Image Backdoor Attack through Mixture of Schrödinger Bridges

This paper focuses on implanting multiple heterogeneous backdoor triggers in bridge-based diffusion models designed for complex and arbitrary input distributions. Existing backdoor formulations mainly address single-attack scenarios and are limited to Gaussian noise input models. To fill this gap...

Structure Disruption: Subverting Malicious Diffusion-Based Inpainting Via Self-Attention Query Perturbation

The rapid advancement of diffusion models has enhanced their image inpainting and editing capabilities but also introduced significant societal risks. Adversaries can exploit user images from social media to generate misleading or harmful content. While adversarial perturbations can disrupt...

CVE-2024-32024

Kohyass is a GUI for Kohya's Stable Diffusion trainers. Kohyass is vulnerable to a path injection in the commongui.py addprepostfix function. This vulnerability is fixed in 23.1.5...

CVE-2024-32023

Kohyass is a GUI for Kohya's Stable Diffusion trainers. Kohyass is vulnerable to a path injection in the commongui.py findandreplace function. This vulnerability is fixed in 23.1.5...

CVE-2024-31462

stable-diffusion-webui is a web interface for Stable Diffusion, implemented using Gradio library. Stable-diffusion-webui 1.7.0 is vulnerable to a limited file write affecting Windows systems. The createui method Backup/Restore tab in modules/uiextensions.py takes user input into the configsavenam...

Revisiting Adversarial Perception Attacks and Defense Methods on Autonomous Driving Systems

Autonomous driving systems ADS increasingly rely on deep learning-based perception models, which remain vulnerable to adversarial attacks. In this paper, we revisit adversarial attacks and defense methods, focusing on road sign recognition and lead object detection and prediction e.g., relative...

CVE-2025-45468

Insecure permissions in fc-stable-diffusion-plus v1.0.18 allows attackers to escalate privileges and compromise the customer cloud account...

CVE-2025-45468

Insecure permissions in fc-stable-diffusion-plus v1.0.18 allows attackers to escalate privileges and compromise the customer cloud account...

PT-2025-22503 · Unknown · Fc-Stable-Diffusion-Plus

Name of the Vulnerable Software and Affected Versions: fc-stable-diffusion-plus version 1.0.18 Description: The issue is related to insecure permissions, which can allow attackers to escalate privileges and compromise the customer cloud account. Recommendations: For fc-stable-diffusion-plus versi...

CVE-2025-45468

CVE-2025-45468 affects fc-stable-diffusion-plus v1.0.18, caused by insecure permissions that enable privilege escalation and potential compromise of the customer cloud account. CVSS 3.1 base score 8.8 (HIGH) with network attack vector, low attack complexity, and privileges required: LOW. Exploita...

fc-stable-diffusion 安全漏洞

fc-stable-diffusion is an open source tool from Serverless Devs Registry for deploying stable-diffusion to AliCloud Functional Computing. A security vulnerability exists in fc-stable-diffusion v1.0.18, which stems from improper privileges and could lead to elevated privileges and customer cloud...

Gaussian Shading++: Rethinking the Realistic Deployment Challenge of Performance-Lossless Image Watermark for Diffusion Models

Ethical concerns surrounding copyright protection and inappropriate content generation pose challenges for the practical implementation of diffusion models. One effective solution involves watermarking the generated images. Existing methods primarily focus on ensuring that watermark embedding doe...

Removing Watermarks with Partial Regeneration Using Semantic Information

As AI-generated imagery becomes ubiquitous, invisible watermarks have emerged as a primary line of defense for copyright and provenance. The newest watermarking schemes embed semantic signals - content-aware patterns that are designed to survive common image manipulations - yet their true...

Real-Time Bit-Level Encryption of Full High-Definition Video without Diffusion

Despite the widespread adoption of Shannon's confusion-diffusion architecture in image encryption, the implementation of diffusion to sequentially establish inter-pixel dependencies for attaining plaintext sensitivity constrains algorithmic parallelism, while the execution of multiple rounds of...

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...

DICOM Compatible, 3D Multimodality Image Encryption Using Hyperchaotic Signal

Medical image encryption plays an important role in protecting sensitive health information from cyberattacks and unauthorized access. In this paper, we introduce a secure and robust encryption scheme that is multi-modality compatible and works with MRI, CT, X-Ray and Ultrasound images for...

Erased but Not Forgotten: How Backdoors Compromise Concept Erasure

The expansion of large-scale text-to-image diffusion models has raised growing concerns about their potential to generate undesirable or harmful content, ranging from fabricated depictions of public figures to sexually explicit images. To mitigate these risks, prior work has devised machine...