Copyright Infringement Risk Reduction via Chain-of-Thought and Task Instruction Prompting

TL;DR

This paper investigates methods to reduce copyright infringement risks in text-to-image models by combining chain-of-thought prompting, task instruction prompting, negative prompting, and prompt re-writing, with experimental analysis on various models.

Contribution

It introduces a formulation integrating multiple prompting strategies to mitigate copyright risks in image generation models, supported by empirical evaluation.

Findings

Chain-of-thought prompting reduces copyrighted content reproduction.

Task instruction prompting improves relevance of generated images.

Combining techniques enhances copyright mitigation effectiveness.

Abstract

Large scale text-to-image generation models can memorize and reproduce their training dataset. Since the training dataset often contains copyrighted material, reproduction of training dataset poses a copyright infringement risk, which could result in legal liabilities and financial losses for both the AI user and the developer. The current works explores the potential of chain-of-thought and task instruction prompting in reducing copyrighted content generation. To this end, we present a formulation that combines these two techniques with two other copyright mitigation strategies: a) negative prompting, and b) prompt re-writing. We study the generated images in terms their similarity to a copyrighted image and their relevance of the user input. We present numerical experiments on a variety of models and provide insights on the effectiveness of the aforementioned techniques for varying model complexity.