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. Beyond verbatim reproduction, models can encode subtler traces of their training data that never surface in their outputs yet remain exploitable. We study this regime for Rectified Flows, which are increasingly used in deployed generative systems. We analyse the interpolation path X_lambda = (1-lambda)X_0 + lambda X_1 that defines the Rectified Flow training. We show that a gap exists between the reconstruction of train and test data that follows a bell-shaped curve over lambda, wich accumulates during training, while the validation metrics remain stable. The signal has a maximum whose location we derive in closed form under Gaussian assumptions. We validate these predictions on both audio and images and show that the bell-shaped structure is universal, while the peak prediction holds when our assumptions are satisfied. As a proof of concept, we exploit this specific lambda-resolved structure to perform a Membership Inference Attack, distinguishing members of the training set from non-members.

Source: arXiv cs.AI | 2026-06-08