UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion

• URL: http://arxiv.org/abs/2601.20325v1
• Date: Wed, 28 Jan 2026 07:42:51 GMT
• Title: UnlearnShield: Shielding Forgotten Privacy against Unlearning Inversion
• Abstract summary: Unlearning aims to remove the influence of specific data from trained models, thereby enhancing privacy protection.<n>Recent research has uncovered critical privacy vulnerabilities, showing that adversaries can exploit unlearning inversion to reconstruct data that was intended to be erased.<n>We propose UnlearnShield, the first defense specifically tailored to counter unlearning inversion.
• Score: 46.86245039541715
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Machine unlearning is an emerging technique that aims to remove the influence of specific data from trained models, thereby enhancing privacy protection. However, recent research has uncovered critical privacy vulnerabilities, showing that adversaries can exploit unlearning inversion to reconstruct data that was intended to be erased. Despite the severity of this threat, dedicated defenses remain lacking. To address this gap, we propose UnlearnShield, the first defense specifically tailored to counter unlearning inversion. UnlearnShield introduces directional perturbations in the cosine representation space and regulates them through a constraint module to jointly preserve model accuracy and forgetting efficacy, thereby reducing inversion risk while maintaining utility. Experiments demonstrate that it achieves a good trade-off among privacy protection, accuracy, and forgetting.

Related papers

• Neural Gate: Mitigating Privacy Risks in LVLMs via Neuron-Level Gradient Gating [71.55435880263238]
  We introduce Neural Gate, a novel method for mitigating privacy risks through neuron-level model editing.<n>Our method improves a model's privacy safeguards by increasing its rate of refusal for privacy-related questions.
  arXiv  Detail & Related papers  (2026-03-13T03:03:20Z)
• Teleportation-Based Defenses for Privacy in Approximate Machine Unlearning [8.735490611482364]
  Approximate machine unlearning aims to efficiently remove the influence of specific data points from a trained model.<n>An adversary with access to pre- and post-unlearning models can exploit their differences for membership inference or data reconstruction.<n>We show these vulnerabilities arise from two factors: large gradient norms of forget-set samples and the close proximity of unlearned parameters to the original model.
  arXiv  Detail & Related papers  (2025-11-29T01:50:33Z)
• Erase or Hide? Suppressing Spurious Unlearning Neurons for Robust Unlearning [31.829376135133554]
  Large language models trained on web-scale data can memorize private or sensitive knowledge, raising significant privacy risks.<n>Some unlearning methods remain vulnerable to "relearning" during subsequent training, allowing a substantial portion of forgotten knowledge to resurface.<n>We introduce Ssiuu, a new class of unlearning methods that employs attribution-guided regularization to prevent spurious negative influence and faithfully remove target knowledge.
  arXiv  Detail & Related papers  (2025-09-26T12:27:23Z)
• CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning [14.061404670832097]
  An effective unlearning method removes the information of the specified data from the trained model, resulting in different outputs for the same input before and after unlearning.<n>We introduce a Compressive Representation Forgetting Unlearning scheme (CRFU) to safeguard against privacy leakage on unlearning.
  arXiv  Detail & Related papers  (2025-02-27T05:59:02Z)
• ExpShield: Safeguarding Web Text from Unauthorized Crawling and Language Modeling Exploitation [17.71790411163849]
  We propose ExpShiled, a proactive self-defense mechanism that mitigates sample-specific memorization via imperceptible text perturbations.<n>Our approach requires no external collaboration while maintaining original readability.<n>Even with privacy backdoors, the Membership Inference Attack (MIA) AUC drops from 0.95 to 0.55, and instance exploitation approaches zero.
  arXiv  Detail & Related papers  (2024-12-30T17:52:02Z)
• Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakage [12.737028324709609]
  Recent legislation obligates organizations to remove requested data and its influence from a trained model. We propose a game-theoretic machine unlearning algorithm that simulates the competitive relationship between unlearning performance and privacy protection.
  arXiv  Detail & Related papers  (2024-11-06T13:47:04Z)
• Ungeneralizable Examples [70.76487163068109]
  Current approaches to creating unlearnable data involve incorporating small, specially designed noises. We extend the concept of unlearnable data to conditional data learnability and introduce textbfUntextbfGeneralizable textbfExamples (UGEs) UGEs exhibit learnability for authorized users while maintaining unlearnability for potential hackers.
  arXiv  Detail & Related papers  (2024-04-22T09:29:14Z)
• Pre-trained Encoders in Self-Supervised Learning Improve Secure and Privacy-preserving Supervised Learning [63.45532264721498]
  Self-supervised learning is an emerging technique to pre-train encoders using unlabeled data. We perform first systematic, principled measurement study to understand whether and when a pretrained encoder can address the limitations of secure or privacy-preserving supervised learning algorithms.
  arXiv  Detail & Related papers  (2022-12-06T21:35:35Z)
• Learning to Invert: Simple Adaptive Attacks for Gradient Inversion in Federated Learning [31.374376311614675]
  Gradient inversion attack enables recovery of training samples from model gradients in federated learning. We show that existing defenses can be broken by a simple adaptive attack.
  arXiv  Detail & Related papers  (2022-10-19T20:41:30Z)
• Protecting Split Learning by Potential Energy Loss [70.81375125791979]
  We focus on the privacy leakage from the forward embeddings of split learning. We propose the potential energy loss to make the forward embeddings become more 'complicated'
  arXiv  Detail & Related papers  (2022-10-18T06:21:11Z)
• Over-the-Air Federated Learning with Privacy Protection via Correlated Additive Perturbations [57.20885629270732]
  We consider privacy aspects of wireless federated learning with Over-the-Air (OtA) transmission of gradient updates from multiple users/agents to an edge server. Traditional perturbation-based methods provide privacy protection while sacrificing the training accuracy. In this work, we aim at minimizing privacy leakage to the adversary and the degradation of model accuracy at the edge server.
  arXiv  Detail & Related papers  (2022-10-05T13:13:35Z)
• Defense Against Gradient Leakage Attacks via Learning to Obscure Data [48.67836599050032]
  Federated learning is considered as an effective privacy-preserving learning mechanism. In this paper, we propose a new defense method to protect the privacy of clients' data by learning to obscure data.
  arXiv  Detail & Related papers  (2022-06-01T21:03:28Z)
• Federated Learning in Adversarial Settings [0.8701566919381224]
  Federated learning scheme provides different trade-offs between robustness, privacy, bandwidth efficiency, and model accuracy. We show that this extension performs as efficiently as the non-private but robust scheme, even with stringent privacy requirements. This suggests a possible fundamental trade-off between Differential Privacy and robustness.
  arXiv  Detail & Related papers  (2020-10-15T14:57:02Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.