One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting

arXiv:2507.07754v3 Announce Type: replace Abstract: Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores. We show that this is not enough. Across 14 representative unlearning methods on CIFAR-10 and SVHN, a single linear map fitted on a held-out calibration set, with no access to the forgotten data, reverses the unlearning in seconds and recovers forget-set accuracy to within a few percent of the original model. Recovered features even support pixel-level reconstruction through a generic decoder. We call this diagnostic Feature Mapping Recovery (FM-recovery). The pattern it exposes is uniform: current unlearning methods do not erase information from the representation, they apply an invertible linear distortion that hides it from one particular prediction head. We propose One-Point Contraction (OPC), an unlearning objective that collapses forget-set features to the origin while leaving the retain-set geometry intact. We prove that this contraction is equivalent to driving the predictive distribution to maximum entropy, so the same mechanism delivers behavioral forgetting and representation-level erasure at once. Forgotten queries land in a region the network treats as out-of-distribution, and the gradient signal on those queries collapses along with their features. OPC is the only method in our benchmark that survives FM-recovery, resists relearning and gradient-inversion attacks, and decouples forget from retain features in entangled settings, all without sacrificing retain or test accuracy.

Abstract:Machine unlearning is usually evaluated by what the classifier outputs: forget-set accuracy, confidence, membership-inference scores. We show that this is not enough. Across 14 representative unlearning methods on CIFAR-10 and SVHN, a single linear map fitted on a held-out calibration set, with no access to the forgotten data, reverses the unlearning in seconds and recovers forget-set accuracy to within a few percent of the original model. Recovered features even support pixel-level reconstruction through a generic decoder. We call this diagnostic Feature Mapping Recovery (FM-recovery). The pattern it exposes is uniform: current unlearning methods do not erase information from the representation, they apply an invertible linear distortion that hides it from one particular prediction head. We propose One-Point Contraction (OPC), an unlearning objective that collapses forget-set features to the origin while leaving the retain-set geometry intact. We prove that this contraction is equivalent to driving the predictive distribution to maximum entropy, so the same mechanism delivers behavioral forgetting and representation-level erasure at once. Forgotten queries land in a region the network treats as out-of-distribution, and the gradient signal on those queries collapses along with their features. OPC is the only method in our benchmark that survives FM-recovery, resists relearning and gradient-inversion attacks, and decouples forget from retain features in entangled settings, all without sacrificing retain or test accuracy.

Machine Learning (cs.LG); Artificial Intelligence (cs.AI)

arXiv:2507.07754 [cs.LG]

(or arXiv:2507.07754v3 [cs.LG] for this version)

https://doi.org/10.48550/arXiv.2507.07754 Focus to learn more arXiv-issued DOI via DataCite

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

aiqbench analysis

One-Point Contraction: Erasing Representational Separability toward Irreversible Deep Forgetting

Related coverage