The Devil is in the Prompts: De-Identification Traces Enhance Memorization Risks in Synthetic Chest X-Ray Generation
Generative models, particularly text-to-image (T2I) diffusion models, play a crucial role in medical image analysis. However, these models are prone to training data memorization, posing significant risks to patient privacy. Synthetic chest X-ray generation is one of the most common applications in medical image analysis with the MIMIC-CXR dataset serving as the primary data repository for this task. This study presents the first systematic attempt to identify prompts and text tokens in MIMIC-CXR that contribute the most to training data memorization. Our analysis reveals two unexpected findings: (1) prompts containing traces of de-identification procedures (markers introduced to hide Protected Health Information) are the most memorized, and (2) among all tokens, de-identification markers contribute the most towards memorization. This highlights a broader issue with the standard anonymization practices and T2I synthesis with MIMIC-CXR. To exacerbate, existing inference-time memorization mitigation strategies are ineffective and fail to sufficiently reduce the model's reliance on memorized text tokens. On this front, we propose actionable strategies for different stakeholders to enhance privacy and improve the reliability of generative models in medical imaging. Finally, our results provide a foundation for future work on developing and benchmarking memorization mitigation techniques for synthetic chest X-ray generation using the MIMIC-CXR dataset. The anonymized code is available at https://anonymous.4open.science/r/diffusion_memorization-8011/
Code (1)
Tasks
BenchmarkingDe-identificationMedical Image AnalysisMemorizationMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Comprehensive and constructive evaluation protocols play an important role in the development of sophisticated text-to-video (T2V) generation models. Existing evaluation protocols primarily focus on temporal consistency …
Text-to-Video GenerationVideo GenerationCopyJudge: Automated Copyright Infringement Identification and Mitigation in Text-to-Image Diffusion Models
Assessing whether AI-generated images are substantially similar to copyrighted works is a crucial step in resolving copyright disputes. In this paper, we propose CopyJudge, an automated copyright infringement identificat…
MemorizationThe Devil is in the Prompts: Retrieval-Augmented Prompt Optimization for Text-to-Video Generation
The evolution of Text-to-video (T2V) generative models, trained on large-scale datasets, has been marked by significant progress. However, the sensitivity of T2V generative models to input prompts highlights the critical…
SentenceText-to-Video GenerationVideo GenerationMemBench: Memorized Image Trigger Prompt Dataset for Diffusion Models
Diffusion models have achieved remarkable success in Text-to-Image generation tasks, leading to the development of many commercial models. However, recent studies have reported that diffusion models often generate replic…
Image GenerationMemorizationText to Image GenerationText-to-Image GenerationPreventing Verbatim Memorization in Language Models Gives a False Sense of Privacy
Studying data memorization in neural language models helps us understand the risks (e.g., to privacy or copyright) associated with models regurgitating training data and aids in the development of countermeasures. Many p…
MemorizationOpen-Ended Question AnsweringStyle Transfer