MGE: A Membership Guided Data Extraction Attack against Diffusion Models
cs.CV
Submitted: 2026-11-07
Updated: 2026-11-07
Terminology
Sources
- The Falcon Series of Open Language Models
- Do Membership Inference Attacks Work on Large Language Models?
- Detecting Adversarial Samples from Artifacts
- Explaining and Harnessing Adversarial Examples
- Model Extraction and Adversarial Transferability, Your BERT is Vulnerable!
- Classifier-Free Diffusion Guidance
- Membership Inference of Diffusion Models
- An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
- DiffWave: A Versatile Diffusion Model for Audio Synthesis
- Towards Black-Box Membership Inference Attack for Diffusion Models
- Scalable Extraction of Training Data from (Production) Language Models
- Black-box Membership Inference Attacks against Fine-tuned Diffusion Models
- White-box Membership Inference Attacks against Diffusion Models
- Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples
- Hierarchical Text-Conditional Image Generation with CLIP Latents
- ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
- Denoising Diffusion Implicit Models
- Membership Inference Attacks on Diffusion Models via Quantile Regression
- LLaMA: Open and Efficient Foundation Language Models
- A Reproducible Extraction of Training Images from Diffusion Models
Related papers
- TEA: Text Encoder Alignment for Robust Concept Erasure in Text-to-Image Models
- Do Egocentric Video-Language Models Capture Both Hand- and Object-Centric Cues?
- Aura: Consistent Multi-Subject Video Generation via VLM-Grounded Semantic Alignment
- PVRF: All-in-one Adverse Weather Removal via Prior-modulated and Velocity-constrained Rectified Flow
- DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
- Out of Sight, Still in Mind: Token Compression for Omni-LLMs