中文
相关论文

相关论文: Robustness of AI-Image Detectors: Fundamental Limi…

200 篇论文

Text-to-image diffusion models, such as Stable Diffusion, have shown exceptional potential in generating high-quality images. However, recent studies highlight concerns over the use of unauthorized data in training these models, which may…

计算机视觉与模式识别 · 计算机科学 2024-11-28 Soumil Datta , Shih-Chieh Dai , Leo Yu , Guanhong Tao

Diffusion models have made substantial advances in recent years, enabling high-quality image synthesis; however, the widespread dissemination and reuse of their outputs have introduced new challenges in intellectual property protection and…

密码学与安全 · 计算机科学 2026-03-11 Yuqi Qian , Yun Cao , Haocheng Fu , Meiyang Lv , Meineng Zhu

Copyright protection for deep neural networks (DNNs) is an urgent need for AI corporations. To trace illegally distributed model copies, DNN watermarking is an emerging technique for embedding and verifying secret identity messages in the…

密码学与安全 · 计算机科学 2023-03-20 Yifan Yan , Xudong Pan , Mi Zhang , Min Yang

In this work, we introduce a novel deep learning-based approach to text-in-image watermarking, a method that embeds and extracts textual information within images to enhance data security and integrity. Leveraging the capabilities of deep…

多媒体 · 计算机科学 2024-04-23 Bishwa Karki , Chun-Hua Tsai , Pei-Chi Huang , Xin Zhong

Recent advances in large-scale text-to-image (T2I) diffusion models have enabled a variety of downstream applications, including style customization, subject-driven personalization, and conditional generation. As T2I models require…

计算机视觉与模式识别 · 计算机科学 2025-04-01 Zilan Wang , Junfeng Guo , Jiacheng Zhu , Yiming Li , Heng Huang , Muhao Chen , Zhengzhong Tu

As policy catches up with the capabilities of generative AI, watermarking is central to content provenance efforts. Inference-time watermarks for autoregressive models are unfit for continuous modalities due to discretization…

机器学习 · 计算机科学 2026-05-26 Georgios Milis , Yubin Qin , Yihan Wu , Heng Huang

Imperceptible digital watermarking is important in copyright protection, misinformation prevention, and responsible generative AI. We propose TrustMark - a GAN-based watermarking method with novel design in architecture and spatio-spectra…

计算机视觉与模式识别 · 计算机科学 2023-12-01 Tu Bui , Shruti Agarwal , John Collomosse

Advances in AI based computer vision has led to a significant growth in synthetic image generation and artificial image tampering with serious implications for unethical exploitations that undermine person identification and could make…

计算机视觉与模式识别 · 计算机科学 2022-08-05 Tahir Hassan , Aras Asaad , Dashti Ali , Sabah Jassim

Watermarking the outputs of generative models has emerged as a promising approach for tracking their provenance. Despite significant interest in autoregressive image generation models and their potential for misuse, no prior work has…

机器学习 · 计算机科学 2025-10-24 Nikola Jovanović , Ismail Labiad , Tomáš Souček , Martin Vechev , Pierre Fernandez

The rapid proliferation of realistic deepfakes has raised urgent concerns over their misuse, motivating the use of defensive watermarks in synthetic images for reliable detection and provenance tracking. However, this defense paradigm…

密码学与安全 · 计算机科学 2026-01-26 Wei Song , Zhenchang Xing , Liming Zhu , Yulei Sui , Jingling Xue

In-generation watermarking for latent diffusion models has recently shown high robustness in marking generated images for easier detection and attribution. However, its application to autoregressive (AR) image models is underexplored.…

计算机视觉与模式识别 · 计算机科学 2026-04-13 Denis Lukovnikov , Andreas Müller , Erwin Quiring , Asja Fischer

From its acquisition in the camera sensors to its storage, different operations are performed to generate the final image. This pipeline imprints specific traces into the image to form a natural watermark. Tampering with an image disturbs…

计算机视觉与模式识别 · 计算机科学 2024-01-17 Matías Tailanian , Marina Gardella , Álvaro Pardo , Pablo Musé

The image deepfake detection task has been greatly addressed by the scientific community to discriminate real images from those generated by Artificial Intelligence (AI) models: a binary classification task. In this work, the deepfake…

计算机视觉与模式识别 · 计算机科学 2023-03-02 Luca Guarnera , Oliver Giudice , Sebastiano Battiato

Watermarking inserts invisible data into content to protect copyright. The embedded information provides proof of authorship and facilitates tracking illegal distribution, etc. Current robust watermarking techniques have been proposed to…

多媒体 · 计算机科学 2018-05-17 Wook-Hyung Kim , Seung-Hun Nam , Ji-Hyeon Kang , Heung-Kyu Lee

The proliferation of AIGC-driven face manipulation and deepfakes poses severe threats to media provenance, integrity, and copyright protection. Prior versatile watermarking systems typically rely on embedding explicit localization payloads,…

计算机视觉与模式识别 · 计算机科学 2026-03-26 Peipeng Yu , Jinfeng Xie , Chengfu Ou , Xiaoyu Zhou , Jianwei Fei , Yunshu Dai , Zhihua Xia , Chip Hong Chang

The rapid proliferation of AI-generated images, powered by generative adversarial networks (GANs), diffusion models, and other synthesis techniques, has raised serious concerns about misinformation, copyright violations, and digital…

计算机视觉与模式识别 · 计算机科学 2026-03-31 Nusrat Tasnim , Kutub Uddin , Khalid Malik

Watermarking the outputs of generative models is a crucial technique for tracing copyright and preventing potential harm from AI-generated content. In this paper, we introduce a novel technique called Tree-Ring Watermarking that robustly…

机器学习 · 计算机科学 2023-07-06 Yuxin Wen , John Kirchenbauer , Jonas Geiping , Tom Goldstein

As artificial intelligence tools become ubiquitous in education, maintaining academic integrity while accommodating pedagogically beneficial AI assistance presents unprecedented challenges. Current AI detection systems fail to control false…

应用统计 · 统计学 2025-08-01 Yangxinyu Xie , Xuyang Chen , Zhimei Ren , Weijie J. Su

To mitigate potential risks associated with language models, recent AI detection research proposes incorporating watermarks into machine-generated text through random vocabulary restrictions and utilizing this information for detection.…

计算与语言 · 计算机科学 2024-02-14 Yu Fu , Deyi Xiong , Yue Dong

The rapid progress in deep generative models has led to the creation of incredibly realistic synthetic images that are becoming increasingly difficult to distinguish from real-world data. The widespread use of Variational Models, Diffusion…

计算机视觉与模式识别 · 计算机科学 2025-01-13 Anant Mehta , Bryant McArthur , Nagarjuna Kolloju , Zhengzhong Tu