中文
相关论文

相关论文: AuthenLoRA: Entangling Stylization with Impercepti…

200 篇论文

Invisible watermarking of AI-generated images can help with copyright protection, enabling detection and identification of AI-generated media. In this work, we present a novel approach to watermark images of T2I Latent Diffusion Models…

计算机视觉与模式识别 · 计算机科学 2025-03-18 Naresh Kumar Devulapally , Mingzhen Huang , Vishal Asnani , Shruti Agarwal , Siwei Lyu , Vishnu Suresh Lokhande

Recent works demonstrate a remarkable ability to customize text-to-image diffusion models while only providing a few example images. What happens if you try to customize such models using multiple, fine-grained concepts in a sequential…

计算机视觉与模式识别 · 计算机科学 2024-05-03 James Seale Smith , Yen-Chang Hsu , Lingyu Zhang , Ting Hua , Zsolt Kira , Yilin Shen , Hongxia Jin

Low-Rank Adaptation (LoRA) has become a widely used method for parameter-efficient fine-tuning of large-scale, pre-trained neural networks. However, LoRA and its extensions face several challenges, including the need for rank adaptivity,…

机器学习 · 计算机科学 2024-10-25 Steffen Schotthöfer , Emanuele Zangrando , Gianluca Ceruti , Francesco Tudisco , Jonas Kusch

Fine-tuning large pre-trained vision foundation models in a parameter-efficient manner is critical for downstream vision tasks, considering the practical constraints of computational and storage costs. Low-rank adaptation (LoRA) is a…

计算机视觉与模式识别 · 计算机科学 2025-03-25 Houqiang Zhong , Shaocheng Shen , Ke Cai , Zhenglong Wu , Jiangchao Yao , Yuan Cheng , Xuefei Li , Xiaoyun Zhang , Li Song , Qiang Hu

As AI advances, copyrighted content faces growing risk of unauthorized use, whether through model training or direct misuse. Building upon invisible adversarial perturbation, recent works developed copyright protections against specific AI…

机器学习 · 计算机科学 2025-06-04 Tianci Liu , Tong Yang , Quan Zhang , Qi Lei

As large language models (LLMs) grow more powerful, concerns over copyright infringement of LLM-generated texts have intensified. LLM watermarking has been proposed to trace unauthorized redistribution or resale of generated content by…

密码学与安全 · 计算机科学 2025-08-05 Qihao Lin , Chen Tang , Lan zhang , Junyang zhang , Xiangyang Li

Deepfake speech attribution remains challenging for existing solutions. Classifier-based solutions often fail to generalize to domain-shifted samples, and watermarking-based solutions are easily compromised by distortions like codec…

音频与语音处理 · 电气工程与系统科学 2025-10-16 Wanying Ge , Xin Wang , Junichi Yamagishi

Fine-tuning text-to-image diffusion models is widely used for personalization and adaptation for new domains. In this paper, we identify a critical vulnerability of fine-tuning: safety alignment methods designed to filter harmful content…

人工智能 · 计算机科学 2024-12-03 Sanghyun Kim , Moonseok Choi , Jinwoo Shin , Juho Lee

In today's digital landscape, the blending of AI-generated and authentic content has underscored the need for copyright protection and content authentication. Watermarking has become a vital tool to address these challenges, safeguarding…

计算机视觉与模式识别 · 计算机科学 2024-12-16 Runyi Hu , Jie Zhang , Yiming Li , Jiwei Li , Qing Guo , Han Qiu , Tianwei Zhang

Low-Rank Adaptation (LoRA) has significantly advanced parameter-efficient fine-tuning of large pretrained models. LoRA augments the pre-trained weights of a model by adding the product of two smaller matrices that together form a low-rank…

人工智能 · 计算机科学 2025-07-09 David Bensaïd , Noam Rotstein , Roy Velich , Daniel Bensaïd , Ron Kimmel

Recent diffusion model customization has shown impressive results in incorporating subject or style concepts with a handful of images. However, the modular composition of multiple concepts into a customized model, aimed to efficiently merge…

计算机视觉与模式识别 · 计算机科学 2025-03-12 Mingkang Zhu , Xi Chen , Zhongdao Wang , Bei Yu , Hengshuang Zhao , Jiaya Jia

Protecting intellectual property on LLM-generated code necessitates effective watermarking systems that can operate within code's highly structured, syntactically constrained nature. In this work, we introduce CodeTracer, an innovative…

密码学与安全 · 计算机科学 2026-05-26 Zhimeng Guo , Huaisheng Zhu , Siyuan Xu , Hangfan Zhang , Teng Xiao , Minhao Cheng

High-fidelity text-to-image diffusion models have revolutionized visual content generation, but their widespread use raises significant ethical concerns, including intellectual property protection and the misuse of synthetic media. To…

计算机视觉与模式识别 · 计算机科学 2025-08-21 Yunzhuo Chen , Naveed Akhtar , Nur Al Hasan Haldar , Ajmal Mian

Image stylization involves manipulating the visual appearance and texture (style) of an image while preserving its underlying objects, structures, and concepts (content). The separation of style and content is essential for manipulating the…

计算机视觉与模式识别 · 计算机科学 2024-09-24 Yarden Frenkel , Yael Vinker , Ariel Shamir , Daniel Cohen-Or

Low-Rank Adaptation (LoRA) has become one of the most widely used fine-tuning mechanisms for adapting large language models to new domains, tasks, and users. Yet adaptation performance alone can obscure an important failure mode: LoRA…

计算与语言 · 计算机科学 2026-05-29 Runze Xu , Arpit Garg , Hemanth Saratchandran , Simon Lucey

Watermarking is a tool for actively identifying and attributing the images generated by latent diffusion models. Existing methods face the dilemma of image quality and watermark robustness. Watermarks with superior image quality usually…

计算机视觉与模式识别 · 计算机科学 2024-09-27 Zheling Meng , Bo Peng , Jing Dong

Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the watermarked text, high detectability, and robustness against…

密码学与安全 · 计算机科学 2025-04-11 Li An , Yujian Liu , Yepeng Liu , Yang Zhang , Yuheng Bu , Shiyu Chang

With the rise of Machine Learning as a Service (MLaaS) platforms,safeguarding the intellectual property of deep learning models is becoming paramount. Among various protective measures, trigger set watermarking has emerged as a flexible and…

密码学与安全 · 计算机科学 2024-04-23 Hongyu Zhu , Sichu Liang , Wentao Hu , Fangqi Li , Ju Jia , Shilin Wang

Protecting intellectual property (IP) of text such as articles and code is increasingly important, especially as sophisticated attacks become possible, such as paraphrasing by large language models (LLMs) or even unauthorized training of…

密码学与安全 · 计算机科学 2024-10-30 Gregory Kang Ruey Lau , Xinyuan Niu , Hieu Dao , Jiangwei Chen , Chuan-Sheng Foo , Bryan Kian Hsiang Low

Text-to-image diffusion models have demonstrated remarkable effectiveness in rapid and high-fidelity personalization, even when provided with only a few user images. However, the effectiveness of personalization techniques has lead to…

计算机视觉与模式识别 · 计算机科学 2025-10-06 Naresh Kumar Devulapally , Shruti Agarwal , Tejas Gokhale , Vishnu Suresh Lokhande