相关论文: Strong Copyright Protection for Language Models vi…

The risk of language models reproducing copyrighted material from their training data has led to the development of various protective measures. Among these, inference-time strategies that impose constraints via post-processing have shown…

There is a growing concern that learned conditional generative models may output samples that are substantially similar to some copyrighted data $C$ that was in their training set. We give a formal definition of $\textit{near…

In this paper, we investigate potential randomization approaches that can complement current practices of input-based methods (such as licensing data and prompt filtering) and output-based methods (such as recitation checker, license…

In this paper, we highlight a critical threat posed by emerging neural models: data plagiarism. We demonstrate how modern neural models (e.g., diffusion models) can replicate copyrighted images, even when protected by advanced watermarking…

Despite significant advancements in image generation using advanced generative frameworks, cross-image integration of content and style remains a key challenge. Current generative models, while powerful, frequently depend on vague textual…

Model fusion research aims to aggregate the knowledge of multiple individual models to enhance performance by combining their weights. In this work, we study the inverse problem: investigating whether model fusion can be used to reduce…

More and more companies' Intellectual Property (IP) is being integrated into Neural Network (NN) models. This IP has considerable value for companies and, therefore, requires adequate protection. For example, an attacker might replicate a…

The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a novel framework with textual embeddings from Pre-trained…

This paper addresses the contentious issue of copyright infringement in images generated by text-to-image models, sparking debates among AI developers, content creators, and legal entities. State-of-the-art models create high-quality…

Large language models (LLMs) commonly risk copyright infringement by reproducing protected content verbatim or with insufficient transformative modifications, posing significant ethical, legal, and practical concerns. Current inference-time…

Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. These models can memorize and generate content similar to their training data, posing potential concerns.…

Imagine a developer who can only change their last line of code, how often would they have to start writing a function from scratch before it is correct? Auto-regressive models for code generation from natural language have a similar…

Current image fusion methods struggle to adapt to real-world environments encompassing diverse degradations with spatially varying characteristics. To address this challenge, we propose a robust fusion controller (RFC) capable of achieving…

Language model continual learning (CL) has recently attracted significant interest for its ability to adapt large language models (LLMs) to dynamic real-world scenarios without retraining. A major challenge in this domain is catastrophic…

Sequence-to-sequence models have recently become very popular for tackling handwritten word recognition problems. However, how to effectively integrate an external language model into such recognizer is still a challenging problem. The main…

While diffusion models demonstrate a remarkable capability for generating high-quality images, their tendency to `replicate' training data raises privacy concerns. Although recent research suggests that this replication may stem from the…

Assessing whether AI-generated images are substantially similar to source works is a crucial step in resolving copyright disputes. In this paper, we propose CopyJudge, a novel automated infringement identification framework that leverages…

Are there any conditions under which a generative model's outputs are guaranteed not to infringe the copyrights of its training data? This is the question of "provable copyright protection" first posed by Vyas, Kakade, and Barak (ICML…

Copyright law confers upon creators the exclusive rights to reproduce, distribute, and monetize their creative works. However, recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. These…

Recent advances in deep learning and computer vision have made the synthesis and counterfeiting of multimedia content more accessible than ever, leading to possible threats and dangers from malicious users. In the audio field, we are…