Cover Image

A Calibrated Memorization Index (MI) for Detecting Training Data Leakage in Generative MRI Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Deo, Yash, Jia, Yan, Lassila, Toni, Hodge, Victoria J, Frang, Alejandro F, Qian, Chenghao, Kang, Siyuan, Habli, Ibrahim
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Metrics that matter: Evaluating image quality metrics for medical image generation
by: Deo, Yash, et al.
Published: (2025)

Out-of-Distribution Detection for Safety Assurance of AI and Autonomous Systems
by: Hodge, Victoria J., et al.
Published: (2025)

Upstream and Downstream AI Safety: Both on the Same River?
by: McDermid, John, et al.
Published: (2024)

WER is Unaware: Assessing How ASR Errors Distort Clinical Understanding in Patient Facing Dialogue
by: Ellis, Zachary, et al.
Published: (2025)

Solving the long-tailed distribution problem by exploiting the synergies and balance of different techniques
by: Wang, Ziheng, et al.
Published: (2025)

Clear, Compelling Arguments: Rethinking the Foundations of Frontier AI Safety Cases
by: Feakins, Shaun, et al.
Published: (2026)

Reduced order modelling of intracranial aneurysm flow using proper orthogonal decomposition and neural networks
by: Michael MacRaild, et al.
Published: (2024)

Leaner Training, Lower Leakage: Revisiting Memorization in LLM Fine-Tuning with LoRA
by: Wang, Fei, et al.
Published: (2025)

Formal Evidence Generation for Assurance Cases for Robotic Software Models
by: Yan, Fang, et al.
Published: (2026)

Memorize Early, Then Query: Inlier-Memorization-Guided Active Outlier Detection
by: Kang, Minseo, et al.
Published: (2026)

Uncovering Latent Memories: Assessing Data Leakage and Memorization Patterns in Frontier AI Models
by: Duan, Sunny, et al.
Published: (2024)

Evaluating Metrics for Safety with LLM-as-Judges
by: Clegg, Kester, et al.
Published: (2025)

ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
by: Zhang, Guangwei, et al.
Published: (2025)

Extracting Memorized Training Data via Decomposition
by: Su, Ellen, et al.
Published: (2024)

The BIG Argument for AI Safety Cases
by: Habli, Ibrahim, et al.
Published: (2025)

Do LLMs Really Memorize Personally Identifiable Information? Revisiting PII Leakage with a Cue-Controlled Memorization Framework
by: Luo, Xiaoyu, et al.
Published: (2026)

How Much Training Data is Memorized in Overparameterized Autoencoders? An Inverse Problem Perspective on Memorization Evaluation
by: Abitbul, Koren, et al.
Published: (2023)

Memorization Sinks: Isolating Memorization during LLM Training
by: Ghosal, Gaurav R., et al.
Published: (2025)

A Novel Metric for Detecting Memorization in Generative Models for Brain MRI Synthesis
by: Scardace, Antonio, et al.
Published: (2025)

Greener Together or Carbon Leakage? What Regional Effect Can Green Credit Policy Bring
by: Zengram Yuanzhen Zheng, et al.
Published: (2025)

Quantifying Memorization and Detecting Training Data of Pre-trained Language Models using Japanese Newspaper
by: Ishihara, Shotaro, et al.
Published: (2024)

The case for delegated AI autonomy for Human AI teaming in healthcare
by: Jia, Yan, et al.
Published: (2025)

CircuitGuard: Mitigating LLM Memorization in RTL Code Generation Against IP Leakage
by: Mashnoor, Nowfel, et al.
Published: (2025)

Robustness of Deep Learning for Accelerated MRI: Benefits of Diverse Training Data
by: Lin, Kang, et al.
Published: (2023)

Uncovering Memorization in Timeseries Imputation models: LBRM Membership Inference and its link to attribute Leakage
by: Taleb, Faiz, et al.
Published: (2026)

Understanding the Impact of Differentially Private Training on Memorization of Long-Tailed Data
by: Zhang, Jiaming, et al.
Published: (2026)

What's my role? Modelling responsibility for AI-based safety-critical systems
by: Ryan, Philippa, et al.
Published: (2023)

Correcting for probe wandering by precession path segmentation
by: Nordahl, Gregory, et al.
Published: (2022)

Memorization or Interpolation ? Detecting LLM Memorization through Input Perturbation Analysis
by: Djiré, Albérick Euraste, et al.
Published: (2025)

Improving Image Data Leakage Detection in Automotive Software
by: Babu, Md Abu Ahammed, et al.
Published: (2024)

Cram Less to Fit More: Training Data Pruning Improves Memorization of Facts
by: Ye, Jiayuan, et al.
Published: (2026)

Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models
by: Patel, Laksh, et al.
Published: (2025)

R-Index: A Robust Metric for IVIM Parameter Estimation on Clinical MRI Scanners
by: Dai, Yan, et al.
Published: (2025)

Challenges in ageing persons with haemophilia
by: Michael Makris, et al.
Published: (2024)

Simulating Training Data Leakage in Multiple-Choice Benchmarks for LLM Evaluation
by: Hidayat, Naila Shafirni, et al.
Published: (2025)

Sequence-Level Leakage Risk of Training Data in Large Language Models
by: Tiwari, Trishita, et al.
Published: (2024)

Data Leakage Detection Using Dynamic Data Structure and Classification Techniques
by: César Byron Guevara Maldonado
Published: (2015)

Calibration of Time-Series Forecasting: Detecting and Adapting Context-Driven Distribution Shift
by: Chen, Mouxiang, et al.
Published: (2023)

The occurrence of seaweed flies (Diptera: Coelopidae) on the Isle of Islay
by: Hodge, S
Published: (1996)

SPARQL Query Generation with LLMs: Measuring the Impact of Training Data Memorization and Knowledge Injection
by: Gashkov, Aleksandr, et al.
Published: (2025)