CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning

• URL: http://arxiv.org/abs/2503.00062v1
• Date: Thu, 27 Feb 2025 05:59:02 GMT
• Title: CRFU: Compressive Representation Forgetting Against Privacy Leakage on Machine Unlearning
• Authors: Weiqi Wang, Chenhan Zhang, Zhiyi Tian, Shushu Liu, Shui Yu,
• Abstract summary: 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.
• Score: 14.061404670832097
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Machine unlearning allows data owners to erase the impact of their specified data from trained models. Unfortunately, recent studies have shown that adversaries can recover the erased data, posing serious threats to user privacy. 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. Adversaries can exploit these output differences to conduct privacy leakage attacks, such as reconstruction and membership inference attacks. However, directly applying traditional defenses to unlearning leads to significant model utility degradation. In this paper, we introduce a Compressive Representation Forgetting Unlearning scheme (CRFU), designed to safeguard against privacy leakage on unlearning. CRFU achieves data erasure by minimizing the mutual information between the trained compressive representation (learned through information bottleneck theory) and the erased data, thereby maximizing the distortion of data. This ensures that the model's output contains less information that adversaries can exploit. Furthermore, we introduce a remembering constraint and an unlearning rate to balance the forgetting of erased data with the preservation of previously learned knowledge, thereby reducing accuracy degradation. Theoretical analysis demonstrates that CRFU can effectively defend against privacy leakage attacks. Our experimental results show that CRFU significantly increases the reconstruction mean square error (MSE), achieving a defense effect improvement of approximately $200\%$ against privacy reconstruction attacks with only $1.5\%$ accuracy degradation on MNIST.

Related papers

• 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)
• Pseudo-Probability Unlearning: Towards Efficient and Privacy-Preserving Machine Unlearning [59.29849532966454]
  We propose PseudoProbability Unlearning (PPU), a novel method that enables models to forget data to adhere to privacy-preserving manner. Our method achieves over 20% improvements in forgetting error compared to the state-of-the-art.
  arXiv  Detail & Related papers  (2024-11-04T21:27:06Z)
• 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)
• Privacy-Preserving Debiasing using Data Augmentation and Machine Unlearning [3.049887057143419]
  Data augmentation exposes machine learning models to privacy attacks, such as membership inference attacks. We propose an effective combination of data augmentation and machine unlearning, which can reduce data bias while providing a provable defense against known attacks.
  arXiv  Detail & Related papers  (2024-04-19T21:54:20Z)
• Reconciling AI Performance and Data Reconstruction Resilience for Medical Imaging [52.578054703818125]
  Artificial Intelligence (AI) models are vulnerable to information leakage of their training data, which can be highly sensitive. Differential Privacy (DP) aims to circumvent these susceptibilities by setting a quantifiable privacy budget. We show that using very large privacy budgets can render reconstruction attacks impossible, while drops in performance are negligible.
  arXiv  Detail & Related papers  (2023-12-05T12:21:30Z)
• No Free Lunch in "Privacy for Free: How does Dataset Condensation Help Privacy" [75.98836424725437]
  New methods designed to preserve data privacy require careful scrutiny. Failure to preserve privacy is hard to detect, and yet can lead to catastrophic results when a system implementing a privacy-preserving'' method is attacked.
  arXiv  Detail & Related papers  (2022-09-29T17:50:23Z)
• RelaxLoss: Defending Membership Inference Attacks without Losing Utility [68.48117818874155]
  We propose a novel training framework based on a relaxed loss with a more achievable learning target. RelaxLoss is applicable to any classification model with added benefits of easy implementation and negligible overhead. Our approach consistently outperforms state-of-the-art defense mechanisms in terms of resilience against MIAs.
  arXiv  Detail & Related papers  (2022-07-12T19:34:47Z)
• Machine unlearning via GAN [2.406359246841227]
  Machine learning models, especially deep models, may unintentionally remember information about their training data. We present a GAN-based algorithm to delete data in deep models, which significantly improves deleting speed compared to retraining from scratch.
  arXiv  Detail & Related papers  (2021-11-22T05:28:57Z)
• Hard to Forget: Poisoning Attacks on Certified Machine Unlearning [13.516740881682903]
  We consider an attacker aiming to increase the computational cost of data removal. We derive and empirically investigate a poisoning attack on certified machine unlearning.
  arXiv  Detail & Related papers  (2021-09-17T01:00:46Z)
• Privacy-Preserving Federated Learning on Partitioned Attributes [6.661716208346423]
  Federated learning empowers collaborative training without exposing local data or models. We introduce an adversarial learning based procedure which tunes a local model to release privacy-preserving intermediate representations. To alleviate the accuracy decline, we propose a defense method based on the forward-backward splitting algorithm.
  arXiv  Detail & Related papers  (2021-04-29T14:49:14Z)
• Sampling Attacks: Amplification of Membership Inference Attacks by Repeated Queries [74.59376038272661]
  We introduce sampling attack, a novel membership inference technique that unlike other standard membership adversaries is able to work under severe restriction of no access to scores of the victim model. We show that a victim model that only publishes the labels is still susceptible to sampling attacks and the adversary can recover up to 100% of its performance. For defense, we choose differential privacy in the form of gradient perturbation during the training of the victim model as well as output perturbation at prediction time.
  arXiv  Detail & Related papers  (2020-09-01T12:54:54Z)

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.