arXiv:2606. 07271v3 Announce Type: replace-cross Abstract: Understanding memorization in generative models remains challenging, with implications for copyright and privacy.
arXiv:2606. 07271v1 Announce Type: cross Abstract: Understanding what generative models retain from training data remains challenging, with implications for copyright and privacy.
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.
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.
arXiv:2601. 21628v2 Announce Type: replace-cross Abstract: Diffusion models have achieved remarkable progress in image generation, but their increasing deployment raises serious concerns about privacy and copyright.
arXiv:2603. 13421v2 Announce Type: replace Abstract: Generative models based on the Flow Matching objective, particularly Rectified Flow, have emerged as a dominant paradigm for efficient, high-fidelity image synthesis.
arXiv:2607. 13541v1 Announce Type: cross Abstract: To overcome data scarcity and privacy constraints in data collection, it has become standard practice across academia and industry to augment real training data with text-to-image (T2I)-generated synthetic data, a paradigm we term Real-Synthetic Mix-Training (RSMT).
The paper addresses the challenge of calibrating membership inference attacks in a one‑round setting where only a single trained model is available. It proposes using neighboring data points of the target to approximate the calibration that reference models normally provide, and demonstrates that querying these neighbors—especially against early training checkpoints—enhances the membership signal. Experiments on three image classification datasets and training setups show that this neighbor‑based approach yields strong attack performance without extra training cost.
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.
arXiv:2603. 17019v2 Announce Type: replace Abstract: A central question in the debate over large language models is whether transformers can learn rules they have never seen, or whether they can only interpolate: predict new cases from their similarity to training examples.
arXiv:2506. 20893v5 Announce Type: replace-cross Abstract: In this paper, we reveal a significant shortcoming in class unlearning evaluations: overlooking the underlying class geometry can cause information leakage about the forgotten class.
arXiv:2510. 10982v2 Announce Type: replace-cross Abstract: Recent AI regulations increasingly emphasize the need for mechanisms that preserve the utility of data for AI innovation while preventing misuse, particularly by enforcing purpose limitation in downstream AI applications.
arXiv:2603.18908v5 Announce Type: replace Abstract: Independently trained language models often learn compatible late-stage representations, despite differences in training objectives, architectures,...