LGAIFeb 28

ROKA: Robust Knowledge Unlearning against Adversaries

Jinmyeong Shin, Joshua Tapia, Nicholas Ferreira, Gabriel Diaz, Moayed Daneshyari, Hyeran Jeon
arXiv:2603.00436v1
Originality Incremental advance
AI Analysis

This addresses data privacy issues in machine learning by mitigating new unlearning-induced attacks, though it appears incremental as it builds on prior unlearning methods.

The paper tackles the problem of knowledge contamination in machine unlearning, where existing methods degrade model performance, and introduces ROKA, a robust unlearning strategy that unlearns targets while preserving or enhancing accuracy on retained data, as shown in evaluations on large models.

The need for machine unlearning is critical for data privacy, yet existing methods often cause Knowledge Contamination by unintentionally damaging related knowledge. Such a degraded model performance after unlearning has been recently leveraged for new inference and backdoor attacks. Most studies design adversarial unlearning requests that require poisoning or duplicating training data. In this study, we introduce a new unlearning-induced attack model, namely indirect unlearning attack, which does not require data manipulation but exploits the consequence of knowledge contamination to perturb the model accuracy on security-critical predictions. To mitigate this attack, we introduce a theoretical framework that models neural networks as Neural Knowledge Systems. Based on this, we propose ROKA, a robust unlearning strategy centered on Neural Healing. Unlike conventional unlearning methods that only destroy information, ROKA constructively rebalances the model by nullifying the influence of forgotten data while strengthening its conceptual neighbors. To the best of our knowledge, our work is the first to provide a theoretical guarantee for knowledge preservation during unlearning. Evaluations on various large models, including vision transformers, multi-modal models, and large language models, show that ROKA effectively unlearns targets while preserving, or even enhancing, the accuracy of retained data, thereby mitigating the indirect unlearning attacks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes