English
Related papers

Related papers: Towards Understanding Unsafe Video Generation

200 papers

We capitalize on large amounts of unlabeled video in order to learn a model of scene dynamics for both video recognition tasks (e.g. action classification) and video generation tasks (e.g. future prediction). We propose a generative…

Computer Vision and Pattern Recognition · Computer Science 2016-10-27 Carl Vondrick , Hamed Pirsiavash , Antonio Torralba

Controllable video generation remains a significant challenge, despite recent advances in generating high-quality and consistent videos. Most existing methods for controlling video generation treat the video as a whole, neglecting intricate…

Computer Vision and Pattern Recognition · Computer Science 2025-10-07 Yifan Shen , Peiyuan Zhu , Zijian Li , Shaoan Xie , Namrata Deka , Zongfang Liu , Zeyu Tang , Guangyi Chen , Kun Zhang

As large language models (LLMs) are increasingly deployed in high-stakes settings, the risk of generating harmful or toxic content remains a central challenge. Post-hoc alignment methods are brittle: once unsafe patterns are learned during…

Malicious or manipulated prompts are known to exploit text-to-image models to generate unsafe images. Existing studies, however, focus on the passive exploitation of such harmful capabilities. In this paper, we investigate the proactive…

Cryptography and Security · Computer Science 2025-02-06 Yixin Wu , Ning Yu , Michael Backes , Yun Shen , Yang Zhang

State-of-the-art 3D-field video-referenced Talking Face Generation (TFG) methods synthesize high-fidelity personalized talking-face videos in real time by modeling 3D geometry and appearance from reference portrait video. This capability…

Computer Vision and Pattern Recognition · Computer Science 2026-01-07 Rui-qing Sun , Xingshan Yao , Tian Lan , Jia-Ling Shi , Chen-Hao Cui , Hui-Yang Zhao , Zhijing Wu , Chen Yang , Xian-Ling Mao

As Large Language Models (LLMs) grow increasingly powerful, ensuring their safety and alignment with human values remains a critical challenge. Ideally, LLMs should provide informative responses while avoiding the disclosure of harmful or…

Computation and Language · Computer Science 2024-10-04 Lingrui Mei , Shenghua Liu , Yiwei Wang , Baolong Bi , Ruibin Yuan , Xueqi Cheng

Recent advancements in deep learning generative models have raised concerns as they can create highly convincing counterfeit images and videos. This poses a threat to people's integrity and can lead to social instability. To address this…

Computer Vision and Pattern Recognition · Computer Science 2024-02-19 Leandro A. Passos , Danilo Jodas , Kelton A. P. da Costa , Luis A. Souza Júnior , Douglas Rodrigues , Javier Del Ser , David Camacho , João Paulo Papa

Video Large Language Models (VideoLLMs) are increasingly deployed on numerous critical applications, where users rely on auto-generated summaries while casually skimming the video stream. We show that this interaction hides a critical…

Multimedia · Computer Science 2025-11-18 Yuxin Cao , Wei Song , Derui Wang , Jingling Xue , Jin Song Dong

Generating video descriptions in natural language (a.k.a. video captioning) is a more challenging task than image captioning as the videos are intrinsically more complicated than images in two aspects. First, videos cover a broader range of…

Computer Vision and Pattern Recognition · Computer Science 2017-09-05 Shizhe Chen , Jia Chen , Qin Jin

Adversarial robustness of deep neural networks has been actively investigated. However, most existing defense approaches are limited to a specific type of adversarial perturbations. Specifically, they often fail to offer resistance to…

Machine Learning · Computer Science 2021-12-15 Shao-Yuan Lo , Vishal M. Patel

Deepfake or synthetic images produced using deep generative models pose serious risks to online platforms. This has triggered several research efforts to accurately detect deepfake images, achieving excellent performance on publicly…

Cryptography and Security · Computer Science 2024-04-26 Sifat Muhammad Abdullah , Aravind Cheruvu , Shravya Kanchi , Taejoong Chung , Peng Gao , Murtuza Jadliwala , Bimal Viswanath

Automatically generating training supervision for embodied tasks is crucial, as manual designing is tedious and not scalable. While prior works use large language models (LLMs) or vision-language models (VLMs) to generate rewards, these…

Computer Vision and Pattern Recognition · Computer Science 2025-03-14 Xiaowen Qiu , Yian Wang , Jiting Cai , Zhehuan Chen , Chunru Lin , Tsun-Hsuan Wang , Chuang Gan

Video generation assessment is essential for ensuring that generative models produce visually realistic, high-quality videos while aligning with human expectations. Current video generation benchmarks fall into two main categories:…

Computer Vision and Pattern Recognition · Computer Science 2025-04-30 Hui Han , Siyuan Li , Jiaqi Chen , Yiwen Yuan , Yuling Wu , Chak Tou Leong , Hanwen Du , Junchen Fu , Youhua Li , Jie Zhang , Chi Zhang , Li-jia Li , Yongxin Ni

We present a novel dataset aimed at advancing danger analysis and assessment by addressing the challenge of quantifying danger in video content and identifying how human-like a Large Language Model (LLM) evaluator is for the same. This is…

Computer Vision and Pattern Recognition · Computer Science 2025-03-03 Pranav Gupta , Advith Krishnan , Naman Nanda , Ananth Eswar , Deeksha Agarwal , Pratham Gohil , Pratyush Goel

Large language models write production code, and yet they routinely introduce well-known vulnerabilities. We show that this is not a knowledge deficit: the same models that generate insecure code, correctly identify and explain the…

Cryptography and Security · Computer Science 2026-04-21 Gustavo Sandoval , Brendan Dolan-Gavitt , Siddharth Garg

Understanding and predicting dynamics of the physical world can enhance a robot's ability to plan and interact effectively in complex environments. While recent video generation models have shown strong potential in modeling dynamic scenes,…

Computer Vision and Pattern Recognition · Computer Science 2026-05-19 Zeyi Liu , Shuang Li , Eric Cousineau , Siyuan Feng , Benjamin Burchfiel , Shuran Song

Recent advances in deep generative models have lead to remarkable progress in synthesizing high quality images. Following their successful application in image processing and representation learning, an important next step is to consider…

Computer Vision and Pattern Recognition · Computer Science 2019-03-28 Thomas Unterthiner , Sjoerd van Steenkiste , Karol Kurach , Raphael Marinier , Marcin Michalski , Sylvain Gelly

Recent advances in image-to-3D models have significantly improved the fidelity and accessibility of 3D content creation. Such a powerful reconstruction capability that enables creative design can also be misused by the adversary to generate…

Cryptography and Security · Computer Science 2026-05-12 Yule Liu , Yilong Yang , Jiale Teng , Hanze Jia , Zeren Luo , Jingyi Zheng , Zifan Peng , Ke Li , Yifan Liao , Zhen Sun , Jiaheng Wei , Yang Liu , Zhuo Ma , Xinlei He

Video generation models (VGMs) have received extensive attention recently and serve as promising candidates for general-purpose large vision models. While they can only generate short videos each time, existing methods achieve long video…

Computer Vision and Pattern Recognition · Computer Science 2024-12-13 Yuanhui Huang , Wenzhao Zheng , Yuan Gao , Xin Tao , Pengfei Wan , Di Zhang , Jie Zhou , Jiwen Lu

The development of AI-Generated Content (AIGC) has empowered the creation of remarkably realistic AI-generated videos, such as those involving Sora. However, the widespread adoption of these models raises concerns regarding potential…

Computer Vision and Pattern Recognition · Computer Science 2024-05-27 Lichuan Ji , Yingqi Lin , Zhenhua Huang , Yan Han , Xiaogang Xu , Jiafei Wu , Chong Wang , Zhe Liu