The Measure of Deception: An Analysis of Data Forging in Machine Unlearning

arXiv:2509.05865 · cs.LG, stat.ML · Submitted 2025-09-06 · Read on arXiv

cs.LG, stat.ML

Submitted: 2025-09-06

Updated: 2026-05-04

Journal ref: Information and Inference: A Journal of the IMA, 15(3), iaag029 (2026)

DOI: 10.1093/imaiai/iaag029

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Machine Unlearning — 2× in this paper · explained in 3 episodes
• Loss Function — 1× in this paper · explained in 2 episodes

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks