Certified Mitigation of Worst-Case LLM Copyright Infringement

• URL: http://arxiv.org/abs/2504.16046v2
• Date: Wed, 23 Apr 2025 16:13:08 GMT
• Title: Certified Mitigation of Worst-Case LLM Copyright Infringement
• Authors: Jingyu Zhang, Jiacan Yu, Marc Marone, Benjamin Van Durme, Daniel Khashabi,
• Abstract summary: "copyright takedown" methods are aimed at preventing models from generating content substantially similar to copyrighted ones.<n>We propose BloomScrub, a remarkably simple yet highly effective inference-time approach that provides certified copyright takedown.<n>Our results suggest that lightweight, inference-time methods can be surprisingly effective for copyright prevention.
• Score: 46.571805194176825
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The exposure of large language models (LLMs) to copyrighted material during pre-training raises concerns about unintentional copyright infringement post deployment. This has driven the development of "copyright takedown" methods, post-training approaches aimed at preventing models from generating content substantially similar to copyrighted ones. While current mitigation approaches are somewhat effective for average-case risks, we demonstrate that they overlook worst-case copyright risks exhibits by the existence of long, verbatim quotes from copyrighted sources. We propose BloomScrub, a remarkably simple yet highly effective inference-time approach that provides certified copyright takedown. Our method repeatedly interleaves quote detection with rewriting techniques to transform potentially infringing segments. By leveraging efficient data sketches (Bloom filters), our approach enables scalable copyright screening even for large-scale real-world corpora. When quotes beyond a length threshold cannot be removed, the system can abstain from responding, offering certified risk reduction. Experimental results show that BloomScrub reduces infringement risk, preserves utility, and accommodates different levels of enforcement stringency with adaptive abstention. Our results suggest that lightweight, inference-time methods can be surprisingly effective for copyright prevention.

Related papers

• SUV: Scalable Large Language Model Copyright Compliance with Regularized Selective Unlearning [22.76025238218253]
  SUV is a selective unlearning framework designed to prevent Large Language Models from memorizing copyrighted content. We replace verbatim copyrighted content with plausible and coherent alternatives. We validate our approach using a large-scale dataset of 500 famous books.
  arXiv  Detail & Related papers  (2025-03-29T02:33:26Z)
• CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models [58.58208005178676]
  We propose CopyJudge, an automated copyright infringement identification framework.<n>We employ an abstraction-filtration-comparison test framework with multi-LVLM debate to assess the likelihood of infringement.<n>Based on the judgments, we introduce a general LVLM-based mitigation strategy.
  arXiv  Detail & Related papers  (2025-02-21T08:09:07Z)
• Copyright-Protected Language Generation via Adaptive Model Fusion [15.48692649098646]
  Copyright-Protecting Model Fusion (CP-Fuse) is a novel approach that combines models trained on disjoint sets of copyrighted material during inference. We show that CP-Fuse significantly reduces the reproduction of protected material without compromising the quality of text and code generation.
  arXiv  Detail & Related papers  (2024-12-09T16:13:17Z)
• CopyrightShield: Spatial Similarity Guided Backdoor Defense against Copyright Infringement in Diffusion Models [61.06621533874629]
  diffusion model is a prime target for copyright infringement attacks. This paper provides an in-depth analysis of the spatial similarity of replication in diffusion model. We propose a novel defense method specifically targeting copyright infringement attacks.
  arXiv  Detail & Related papers  (2024-12-02T14:19:44Z)
• RLCP: A Reinforcement Learning-based Copyright Protection Method for Text-to-Image Diffusion Model [42.77851688874563]
  We propose a Reinforcement Learning-based Copyright Protection(RLCP) method for Text-to-Image Diffusion Model.<n>Our approach minimizes the generation of copyright-infringing content while maintaining the quality of the model-generated dataset.
  arXiv  Detail & Related papers  (2024-08-29T15:39:33Z)
• Can Watermarking Large Language Models Prevent Copyrighted Text Generation and Hide Training Data? [62.72729485995075]
  We investigate the effectiveness of watermarking as a deterrent against the generation of copyrighted texts.<n>We find that watermarking adversely affects the success rate of Membership Inference Attacks (MIAs)<n>We propose an adaptive technique to improve the success rate of a recent MIA under watermarking.
  arXiv  Detail & Related papers  (2024-07-24T16:53:09Z)
• Evaluating Copyright Takedown Methods for Language Models [100.38129820325497]
  Language models (LMs) derive their capabilities from extensive training on diverse data, including potentially copyrighted material. This paper introduces the first evaluation of the feasibility and side effects of copyright takedowns for LMs. We examine several strategies, including adding system prompts, decoding-time filtering interventions, and unlearning approaches.
  arXiv  Detail & Related papers  (2024-06-26T18:09:46Z)
• SHIELD: Evaluation and Defense Strategies for Copyright Compliance in LLM Text Generation [24.644101178288476]
  Large Language Models (LLMs) have transformed machine learning but raised significant legal concerns. LLMs may infringe on copyrights or overly restrict non-copyrighted texts. We propose lightweight, real-time defense to prevent the generation of copyrighted text.
  arXiv  Detail & Related papers  (2024-06-18T18:00:03Z)
• A Dataset and Benchmark for Copyright Infringement Unlearning from Text-to-Image Diffusion Models [52.49582606341111]
  Copyright law confers creators the exclusive rights to reproduce, distribute, and monetize their creative works. Recent progress in text-to-image generation has introduced formidable challenges to copyright enforcement. We introduce a novel pipeline that harmonizes CLIP, ChatGPT, and diffusion models to curate a dataset.
  arXiv  Detail & Related papers  (2024-01-04T11:14:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.