Imagen de Portada

Unlocking Post-hoc Dataset Inference with Synthetic Data

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhao, Bihe, Maini, Pratyush, Boenisch, Franziska, Dziedzic, Adam
Formato:	Preprint
Publicado:	2025
Materias:	Machine Learning Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
por: Hintersdorf, Dominik, et al.
Publicado: (2024)

BitMark: Watermarking Bitwise Autoregressive Image Generative Models
por: Kerner, Louis, et al.
Publicado: (2025)

Have it your way: Individualized Privacy Assignment for DP-SGD
por: Boenisch, Franziska, et al.
Publicado: (2023)

LLM Dataset Inference: Did you train on my dataset?
por: Maini, Pratyush, et al.
Publicado: (2024)

Curation Leaks: Membership Inference Attacks against Data Curation for Machine Learning
por: Wahdany, Dariush, et al.
Publicado: (2026)

Captured by Captions: On Memorization and its Mitigation in CLIP Models
por: Wang, Wenhao, et al.
Publicado: (2025)

Finding DoRI: Discovery of Retained Images in Diffusion Models
por: Kowalczuk, Antoni, et al.
Publicado: (2025)

Peeking Behind Closed Doors: Risks of LLM Evaluation by Private Data Curators
por: Bansal, Hritik, et al.
Publicado: (2025)

Localizing and Mitigating Memorization in Image Autoregressive Models
por: Kasliwal, Aditya, et al.
Publicado: (2025)

ADAGE: Active Defenses Against GNN Extraction
por: Xu, Jing, et al.
Publicado: (2025)

CDI: Copyrighted Data Identification in Diffusion Models
por: Dubiński, Jan, et al.
Publicado: (2024)

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

Memorization in Graph Neural Networks
por: Jamadandi, Adarsh, et al.
Publicado: (2025)

DP-GPL: Differentially Private Graph Prompt Learning
por: Xu, Jing, et al.
Publicado: (2025)

In Defence of Post-hoc Explainability
por: Oh, Nick
Publicado: (2024)

Implementing Adaptations for Vision AutoRegressive Model
por: Shaikh, Kaif, et al.
Publicado: (2025)

Radioactive Watermarks in Diffusion and Autoregressive Image Generative Models
por: Meintz, Michel, et al.
Publicado: (2025)

Privacy Attacks on Image AutoRegressive Models
por: Kowalczuk, Antoni, et al.
Publicado: (2025)

Localizing Memorization in SSL Vision Encoders
por: Wang, Wenhao, et al.
Publicado: (2024)

Differentially Private Prototypes for Imbalanced Transfer Learning
por: Wahdany, Dariush, et al.
Publicado: (2024)

Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)
por: Olatunji, Iyiola E., et al.
Publicado: (2025)

Unifying Post-hoc Explanations of Knowledge Graph Completions
por: Lonardi, Alessandro, et al.
Publicado: (2025)

Post-hoc Interpretability Illumination for Scientific Interaction Discovery
por: Zhang, Ling, et al.
Publicado: (2024)

Valid Inference with Imperfect Synthetic Data
por: Byun, Yewon, et al.
Publicado: (2025)

On the Privacy Risk of In-context Learning
por: Duan, Haonan, et al.
Publicado: (2024)

PXGen: A Post-hoc Explainable Method for Generative Models
por: Huang, Yen-Lung, et al.
Publicado: (2025)

Informative Perturbation Selection for Uncertainty-Aware Post-hoc Explanations
por: Chugh, Sumedha, et al.
Publicado: (2026)

Hard Examples Are All You Need: Maximizing GRPO Post-Training Under Annotation Budgets
por: Pikus, Benjamin, et al.
Publicado: (2025)

Fuzzy Logic Function as a Post-hoc Explanator of the Nonlinear Classifier
por: Klimo, Martin, et al.
Publicado: (2024)

A Synthetic Dataset for Personal Attribute Inference
por: Yukhymenko, Hanna, et al.
Publicado: (2024)

Understanding Post-hoc Explainers: The Case of Anchors
por: Lopardo, Gianluigi, et al.
Publicado: (2023)

Differentially Private Federated Learning With Time-Adaptive Privacy Spending
por: Kiani, Shahrzad, et al.
Publicado: (2025)

A Technical Exploration of Causal Inference with Hybrid LLM Synthetic Data
por: Kim, Dana, et al.
Publicado: (2025)

Explaining Time Series Classifiers with PHAR: Rule Extraction and Fusion from Post-hoc Attributions
por: Mozolewski, Maciej, et al.
Publicado: (2025)

Explaining Neural Networks in Preference Learning: a Post-hoc Inductive Logic Programming Approach
por: Fossemò, Daniele, et al.
Publicado: (2026)

Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation
por: Chun, Yongchan, et al.
Publicado: (2026)

Explanations as Bias Detectors: A Critical Study of Local Post-hoc XAI Methods for Fairness Exploration
por: Papanikou, Vasiliki, et al.
Publicado: (2025)

Conditioned Activation Transport for T2I Safety Steering
por: Chrabąszcz, Maciej, et al.
Publicado: (2026)

Generative Synthetic Data for Causal Inference: Pitfalls, Remedies, and Opportunities
por: Xu, Yichen
Publicado: (2026)

Efficient Model-Stealing Attacks Against Inductive Graph Neural Networks
por: Podhajski, Marcin, et al.
Publicado: (2024)