PROVE: Training-Free Prompt Recovery using Verifiable Evidence

• URL: http://arxiv.org/abs/2608.13671v1
• Date: Thu, 13 Aug 2026 18:08:00 GMT
• Title: PROVE: Training-Free Prompt Recovery using Verifiable Evidence
• Abstract summary: We introduce PROVE (Prompt Recovery with Verified Evidence), a training-free, black-box prompt inversion attack.<n>It reconstructs prompts by composing verifiable scene descriptions rather than optimizing token sequences.<n>The resulting prompts are fully auditable, with every recovered claim grounded in explicit image evidence.
• Score: 5.5813258856679555
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern text-to-image models can generate highly realistic images from natural-language prompts, while recent advances in prompt inversion have made it increasingly feasible to recover those prompts from generated outputs, raising new concerns for copyright protection and content ownership. As prompt marketplaces emerge, recovered prompts can enable both the unauthorized reproduction and redistribution of copyrighted creative works, and the exposure of the prompts that encode an artist's creative recipe in AI-generated content. Existing prompt inversion methods rely on gradient-based optimization, autoregressive captioning, or reinforcement learning. However, optimization-based methods often produce unreadable prompts, captioning methods hallucinate unverified details, and RL-based approaches frequently overfit to specific generators while introducing evaluation circularity. We introduce PROVE (Prompt Recovery with Verified Evidence), a training-free, black-box prompt inversion attack that reconstructs prompts by composing verifiable scene descriptions rather than optimizing token sequences, targeting both original copyrighted works and AI-generated content. The resulting prompts are fully auditable, with every recovered claim grounded in explicit image evidence, and are formalized through a precision-constrained recall maximization objective. Across MS-COCO, Flickr30K, and Lexica, using state-of-the-art text-to-image generators, PROVE consistently outperforms optimization, captioning, and RL-based baselines on image similarity (DINO, LPIPS) and text-image alignment (CLIP), without any training, generator access, or fine-tuning, demonstrating a stronger and more practical prompt inversion attack.

Related papers

• PRISM: Prompt Refinement via Image-grounded Self-rewarding Mechanism for Text-to-Image Generation [6.601249008729316]
  We propose PRISM, a Prompt Refinement optimisation framework via Image-grounded Self-rewarding Mechanism.<n>PRISM closes the prompt-image-feedback loop by interpreting generated images with structured visual diagnosis.<n>Experiments show that PRISM improves holistic image quality and fine-grained semantic alignment.
  arXiv  Detail & Related papers  (2026-07-27T12:31:32Z)
• PromptEvolver: Prompt Inversion through Evolutionary Optimization in Natural-Language Space [20.416910591388618]
  We present PromptEvolver, a prompt inversion approach that generates natural-language prompts while achieving high-fidelity reconstructions of the target image.<n>Our method uses a genetic algorithm to optimize the prompt, leveraging a strong vision-language model to guide the evolution process.
  arXiv  Detail & Related papers  (2026-04-03T17:00:49Z)
• Mitigating Memorization in Text-to-Image Diffusion via Region-Aware Prompt Augmentation and Multimodal Copy Detection [53.789057575175065]
  Region-Aware Prompt Augmentation (RAPTA) and Attention-Driven Multimodal Copy Detection (ADMCD) are presented.<n>RAPTA uses an object detector to find salient regions and turn them into semantically grounded prompt variants.<n>ADMCD aggregates local patch, global semantic, and texture cues with a lightweight transformer to produce a fused representation.<n>Experiments show that RAPTA reduces overfitting while maintaining high synthesis quality, and that ADMCD reliably detects copying, outperforming single-modal metrics.
  arXiv  Detail & Related papers  (2026-03-13T15:16:27Z)
• Copyright Infringement Risk Reduction via Chain-of-Thought and Task Instruction Prompting [7.04790342345686]
  reproduction of training dataset poses a copyright infringement risk.<n>We present a formulation that combines chain-of-thought and task instruction prompting in reducing copyrighted content generation.<n>We study the generated images in terms their similarity to a copyrighted image and their relevance to the user input.
  arXiv  Detail & Related papers  (2025-12-17T13:39:17Z)
• EDITOR: Effective and Interpretable Prompt Inversion for Text-to-Image Diffusion Models [41.63451923844824]
  We propose a prompt inversion technique called sys for text-to-image diffusion models.<n>Our method outperforms existing methods in terms of image similarity, textual alignment, prompt interpretability and generalizability.
  arXiv  Detail & Related papers  (2025-06-03T16:44:15Z)
• RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning [88.14234949860105]
  RePrompt is a novel reprompting framework that introduces explicit reasoning into the prompt enhancement process via reinforcement learning.<n>Our approach enables end-to-end training without human-annotated data.
  arXiv  Detail & Related papers  (2025-05-23T06:44:26Z)
• CopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models [58.58208005178676]
  We propose CopyJudge, a novel automated infringement identification framework.<n>We employ an abstraction-filtration-comparison test framework to assess the likelihood of infringement.<n>We introduce a general LVLM-based mitigation strategy that automatically optimize infringing prompts.
  arXiv  Detail & Related papers  (2025-02-21T08:09:07Z)
• Decoder Pre-Training with only Text for Scene Text Recognition [54.93037783663204]
  Scene text recognition (STR) pre-training methods have achieved remarkable progress, primarily relying on synthetic datasets. We introduce a novel method named Decoder Pre-training with only text for STR (DPTR) DPTR treats text embeddings produced by the CLIP text encoder as pseudo visual embeddings and uses them to pre-train the decoder.
  arXiv  Detail & Related papers  (2024-08-11T06:36:42Z)
• Dynamic Prompt Optimizing for Text-to-Image Generation [63.775458908172176]
  We introduce the textbfPrompt textbfAuto-textbfEditing (PAE) method to improve text-to-image generative models. We employ an online reinforcement learning strategy to explore the weights and injection time steps of each word, leading to the dynamic fine-control prompts.
  arXiv  Detail & Related papers  (2024-04-05T13:44:39Z)
• Prompt Expansion for Adaptive Text-to-Image Generation [51.67811570987088]
  This paper proposes a Prompt Expansion framework that helps users generate high-quality, diverse images with less effort. The Prompt Expansion model takes a text query as input and outputs a set of expanded text prompts. We conduct a human evaluation study that shows that images generated through Prompt Expansion are more aesthetically pleasing and diverse than those generated by baseline methods.
  arXiv  Detail & Related papers  (2023-12-27T21:12:21Z)

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.