arXiv AI June 24, 2026 By Bihe Zhao, Michel Meintz, Juangui Xu, Franziska Boenisch, Adam Dziedzic

MGI: Member vs Generated Inference

arXiv:2606. 23872v1 Announce Type: cross Abstract: As generative models increasingly produce samples that are indistinguishable from human-created content, it becomes difficult to determine whether a given data point was part of a model's natural training set or was generated by the model itself, especially when models memorize and reproduce training data.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

diffusion

arXiv AI

Jun 2

GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning

arXiv:2601. 22651v2 Announce Type: replace-cross Abstract: Training-data attribution for vision generative models aims to identify which training data influenced a given output.

By Naoki Murata, Yuhta Takida, Chieh-Hsin Lai, Toshimitsu Uesaka, Bac Nguyen, Stefano Ermon, Yuki Mitsufuji

diffusion

arXiv AI

Jul 7

One Framework for All: Cross-Modal Membership Inference for Generative Models

arXiv:2607. 04339v1 Announce Type: cross Abstract: Large generative models across text-to-text, text-to-image, and image-to-text modalities have been shown to pose significant privacy risks.

By Dayong Ye, Tainqing Zhu, Kun Gao, Junhao Liu, Yichuan Chen, Shuai Zhou, Hengzhu Liu, Bo Liu, Wanlei Zhou

rag diffusion fine-tuning multimodal benchmarks safety

arXiv Machine Learning

Aug 4

Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection

arXiv:2608. 00716v1 Announce Type: cross Abstract: Robust detection of generated images is critical to counter the misuse of generative models.

By Jun Nie, Yonggang Zhang, Tongliang Liu, Yiu-ming Cheung, Bo Han, Xinmei Tian

benchmarks

arXiv AI

Jul 1

Amplifying Membership Signal Through Chained Regeneration

arXiv:2606. 31991v1 Announce Type: cross Abstract: The tendency of large generative models to memorize training data makes sample verification critical for privacy auditing and copyright enforcement.

By Wojciech {\L}apacz, Stanis{\l}aw Pawlak

llms diffusion safety

arXiv Machine Learning

Jun 26

Dataset Usage Inference without Shadow Models or Held-out Data

arXiv:2606. 26257v1 Announce Type: new Abstract: How much of my data was used to train a machine learning model?

By Wojciech {\L}apacz, Stanis{\l}aw Pawlak, Jan Dubi\'nski, Franziska Boenisch, Adam Dziedzic

arXiv AI

Jun 8

Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path

arXiv:2606. 07271v1 Announce Type: cross Abstract: Understanding what generative models retain from training data remains challenging, with implications for copyright and privacy.

By Thomas Sesmat, Gabriel Meseguer-Brocal, Geoffroy Peeters

safety

Related stories

GUDA: Counterfactual Group-wise Training Data Attribution for Diffusion Models via Unlearning

One Framework for All: Cross-Modal Membership Inference for Generative Models

Generated Images Are Easier to Forget: A Machine Unlearning Perspective for Synthetic Image Detection

Amplifying Membership Signal Through Chained Regeneration

Dataset Usage Inference without Shadow Models or Held-out Data

Where Rectified Flows Leak: Characterising Membership Signals Along the Interpolation Path