On-the-go Forgetting without Explicit Unlearning via ERASE
Abstract
Existing unlearning approaches typically rely on post hoc weight adaptation or distillation, leading to duplicated memory costs, degraded generalization, and limited scalability. In this work, we introduce ERASE, Erasure via Reconstructive Adversarial Signal Editing, a framework for on-the-go forgetting that suppresses the observable influence of private data without modifying model weights. ERASE leverages structured, class-conditioned input perturbations to induce selective forgetting during inference, eliminating the need for retraining, fine-tuning, or model copies. We rigorously characterize sufficient conditions when ERASE provably achieves functional forgetting of designated subclasses while preserving predictions across other subclasses within the same superclass. This analysis offers a principled foundation for inference-time forgetting under mild regularity assumptions. Across diverse architectures and benchmark datasets, ERASE maintains the best observed balance between forgetting efficacy, computational efficiency, and retention fidelity over recent unlearning-based methods. By reimagining data removal as forgetting without unlearning, our work establishes a scalable, regulation-aligned pathway for continual, privacy-conscious learning.
Related
- Forgetting matters: when subspace optimization accelerates without the strong convexity parameter
- Can Spontaneous Time-Translation Symmetry Breaking Be Quantized Without Explicit Branches?
- Small graphs without power-of-two cycles: a lower bound of 24, a correction to a construction of Exoo, and explicit bounds for f(k)
- Puncture-Forgetting Maps for Measured Foliations and Applications in Teichmüller Space and Complex Dynamics
- Risk-Aware Output Control Should be the Focus of Machine Unlearning
BibTeX
@misc{chakrabarti2026onthego,
title = {{On-the-go Forgetting without Explicit Unlearning via ERASE}},
author = {Kushal Chakrabarti and Mayank Baranwal},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.05966},
eprint = {2609.05966},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.05966},
}
RIS
TY - UNPB
TI - On-the-go Forgetting without Explicit Unlearning via ERASE
AU - Kushal Chakrabarti
AU - Mayank Baranwal
PY - 2026
DA - 2026/09/05
PB - arXiv
DO - 10.48550/arxiv.2609.05966
UR - https://arxiv.org/abs/2609.05966
AB - Existing unlearning approaches typically rely on post hoc weight adaptation or distillation, leading to duplicated memory costs, degraded generalization, and limited scalability. In this work, we introduce ERASE, Erasure via Reconstructive Adversarial Signal Editing, a framework for on-the-go forgetting that suppresses the observable influence of private data without modifying model weights. ERASE leverages structured, class-conditioned input perturbations to induce selective forgetting during inference, eliminating the need for retraining, fine-tuning, or model copies. We rigorously characterize sufficient conditions when ERASE provably achieves functional forgetting of designated subclasses while preserving predictions across other subclasses within the same superclass. This analysis offers a principled foundation for inference-time forgetting under mild regularity assumptions. Across diverse architectures and benchmark datasets, ERASE maintains the best observed balance between forgetting efficacy, computational efficiency, and retention fidelity over recent unlearning-based methods. By reimagining data removal as forgetting without unlearning, our work establishes a scalable, regulation-aligned pathway for continual, privacy-conscious learning.
ER -