English
Related papers

Related papers: 3DEditSafe: Defending 3D Editing Pipelines from Un…

200 papers

Drag-based editing has become popular in 2D content creation, driven by the capabilities of image generative models. However, extending this technique to 3D remains a challenge. Existing 3D drag-based editing methods, whether employing…

Computer Vision and Pattern Recognition · Computer Science 2024-10-22 Honghua Chen , Yushi Lan , Yongwei Chen , Yifan Zhou , Xingang Pan

The advent of 3D Gaussian Splatting (3DGS) has revolutionized 3D editing, offering efficient, high-fidelity rendering and enabling precise local manipulations. Currently, diffusion-based 2D editing models are harnessed to modify multi-view…

Graphics · Computer Science 2025-02-18 Yuxuan Wang , Xuanyu Yi , Zike Wu , Na Zhao , Long Chen , Hanwang Zhang

As 3D Gaussian Splatting (3DGS) gains rapid adoption in safety-critical tasks for efficient novel-view synthesis from static images, how might an adversary tamper images to cause harm? We introduce ComplicitSplat, the first attack that…

Computer Vision and Pattern Recognition · Computer Science 2025-09-09 Matthew Hull , Haoyang Yang , Pratham Mehta , Mansi Phute , Aeree Cho , Haorang Wang , Matthew Lau , Wenke Lee , Wilian Lunardi , Martin Andreoni , Duen Horng Chau

3D Gaussian Splatting (3DGS) has become a state-of-the-art framework for real-time, high-fidelity novel view synthesis. However, its substantial storage requirements and inherently unstructured representation pose challenges for deployment…

Computer Vision and Pattern Recognition · Computer Science 2026-04-14 Yuqin Lu , Yang Zhou , Yihua Dai , Guiqing Li , Shengfeng He

Various (text) prompt filters and (image) safety checkers have been implemented to mitigate the misuse of Text-to-Image (T2I) models in creating Not-Safe-For-Work (NSFW) content. In order to expose potential security vulnerabilities of such…

Cryptography and Security · Computer Science 2025-08-12 Song Yan , Hui Wei , Jinlong Fei , Guoliang Yang , Zhengyu Zhao , Zheng Wang

Identity-preserving models have led to notable progress in generating personalized content. Unfortunately, such models also exacerbate risks when misused, for instance, by generating threatening content targeting specific individuals. This…

Cryptography and Security · Computer Science 2025-12-19 Junming Fu , Jishen Zeng , Yi Jiang , Peiyu Zhuang , Baoying Chen , Siyu Lu , Jianquan Yang

Score distillation sampling (SDS) has emerged as an effective framework in text-driven 3D editing tasks, leveraging diffusion models for 3D-consistent editing. However, existing SDS-based 3D editing methods suffer from long training times…

Computer Vision and Pattern Recognition · Computer Science 2025-02-12 Jiwook Kim , Seonho Lee , Jaeyo Shin , Jiho Choi , Hyunjung Shim

Recent Text-to-Image (T2I) models based on rectified-flow transformers (e.g., SD3, FLUX) achieve high generative fidelity but remain vulnerable to unsafe semantics, especially when triggered by multi-token interactions. Existing mitigation…

Computer Vision and Pattern Recognition · Computer Science 2026-04-03 Xiang Yang , Feifei Li , Mi Zhang , Geng Hong , Xiaoyu You , Min Yang

Recent advancements in 3D diffusion-based semantic scene generation have gained attention. However, existing methods rely on unconditional generation and require multiple resampling steps when editing scenes, which significantly limits…

Computer Vision and Pattern Recognition · Computer Science 2024-11-20 Haowen Zheng , Yanyan Liang

3D scene representation methods like Neural Radiance Fields (NeRF) and 3D Gaussian Splatting (3DGS) have significantly advanced novel view synthesis. As these methods become prevalent, addressing their vulnerabilities becomes critical. We…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Bo-Hsu Ke , You-Zhe Xie , Yu-Lun Liu , Wei-Chen Chiu

Recent text-to-image (T2I) models have exhibited remarkable performance in generating high-quality images from text descriptions. However, these models are vulnerable to misuse, particularly generating not-safe-for-work (NSFW) content, such…

Computer Vision and Pattern Recognition · Computer Science 2026-05-12 Lingzhi Yuan , Xinfeng Li , Chejian Xu , Guanhong Tao , Xiaojun Jia , Yihao Huang , Wei Dong , Yang Liu , Bo Li

Engineering design optimization requires an efficient combination of a 3D shape representation, an optimization algorithm, and a design performance evaluation method, which is often computationally expensive. We present a prompt evolution…

Artificial Intelligence · Computer Science 2024-08-13 Melvin Wong , Thiago Rios , Stefan Menzel , Yew Soon Ong

The identification and removal of systematic errors in object detectors can be a prerequisite for their deployment in safety-critical applications like automated driving and robotics. Such systematic errors can for instance occur under very…

Computer Vision and Pattern Recognition · Computer Science 2023-09-26 Valentyn Boreiko , Matthias Hein , Jan Hendrik Metzen

Text-to-Image (T2I) diffusion models have demonstrated strong generation ability, but their potential to generate unsafe content raises significant safety concerns. Existing inference-time defense methods typically perform category-agnostic…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Binhong Tan , Zhaoxin Wang , Handing Wang

Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversarial prompts, which can bypass safety measures and produce…

Cryptography and Security · Computer Science 2025-10-16 Peigui Qi , Kunsheng Tang , Wenbo Zhou , Weiming Zhang , Nenghai Yu , Tianwei Zhang , Qing Guo , Jie Zhang

3D Gaussian Splatting (3DGS) has shown great potential in autonomous driving simulation and data generation, enabling photorealistic reconstruction and flexible scene manipulation. However, existing 3DGS scene editing methods have limited…

Computer Vision and Pattern Recognition · Computer Science 2026-05-26 Feng Zhou , Jian Zhang , Yuhang Sun , He Wang , Qiong Wen , Debao Kong , Tieru Wu , Rui Ma

Recent works learn 3D representation explicitly under text-3D guidance. However, limited text-3D data restricts the vocabulary scale and text control of generations. Generators may easily fall into a stereotype concept for certain text…

Computer Vision and Pattern Recognition · Computer Science 2024-03-15 Tianyu Huang , Yihan Zeng , Bowen Dong , Hang Xu , Songcen Xu , Rynson W. H. Lau , Wangmeng Zuo

With the recent development of generative models, Text-to-3D generations have also seen significant growth, opening a door for creating video-game 3D assets from a more general public. Nonetheless, people without any professional 3D editing…

Computer Vision and Pattern Recognition · Computer Science 2024-08-12 Zhaoning Wang , Ming Li , Chen Chen

Feed-forward 3D reconstruction has revolutionized 3D vision, providing a powerful baseline for downstream tasks such as novel-view synthesis with 3D Gaussian Splatting. Previous works explore fixing the corrupted rendering results with a…

Computer Vision and Pattern Recognition · Computer Science 2026-03-18 Yiming Huang , Baixiang Huang , Beilei Cui , Chi Kit Ng , Long Bai , Hongliang Ren

Recent advances in 4D Gaussian Splatting (4DGS) editing still face challenges with view, temporal, and non-editing region consistency, as well as with handling complex text instructions. To address these issues, we propose 4DGS-Craft, a…

Computer Vision and Pattern Recognition · Computer Science 2025-10-03 Lei Liu , Can Wang , Zhenghao Chen , Dong Xu