SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts

TL;DR

SecureT2I is a framework that prevents unauthorized editing of AI-generated images by making forbidden images semantically ambiguous, ensuring ethical use while maintaining high-quality manipulation for permitted images.

Contribution

We introduce SecureT2I, a lightweight fine-tuning method that enforces semantic ambiguity on forbidden images to prevent unauthorized edits in diffusion models.

Findings

SecureT2I effectively blocks unauthorized edits on forbidden images.

The method maintains high-quality manipulations on permitted images.

Resize-based vagueness strategy offers optimal trade-offs.

Abstract

Text-guided image manipulation with diffusion models enables flexible and precise editing based on prompts, but raises ethical and copyright concerns due to potential unauthorized modifications. To address this, we propose SecureT2I, a secure framework designed to prevent unauthorized editing in diffusion-based generative models. SecureT2I is compatible with both general-purpose and domain-specific models and can be integrated via lightweight fine-tuning without architectural changes. We categorize images into a permit set and a forbid set based on editing permissions. For the permit set, the model learns to perform high-quality manipulations as usual. For the forbid set, we introduce training objectives that encourage vague or semantically ambiguous outputs (e.g., blurred images), thereby suppressing meaningful edits. The core challenge is to block unauthorized editing while preserving editing quality for permitted inputs. To this end, we design separate loss functions that guide selective editing behavior. Extensive experiments across multiple datasets and models show that SecureT2I effectively degrades manipulation quality on forbidden images while maintaining performance on permitted ones. We also evaluate generalization to unseen inputs and find that SecureT2I consistently outperforms baselines. Additionally, we analyze different vagueness strategies and find that resize-based degradation offers the best trade-off for secure manipulation control.