Protecting Split Learning by Potential Energy Loss

• URL: http://arxiv.org/abs/2210.09617v2
• Date: Wed, 29 May 2024 03:27:49 GMT
• Title: Protecting Split Learning by Potential Energy Loss
• Authors: Fei Zheng, Chaochao Chen, Lingjuan Lyu, Xinyi Fu, Xing Fu, Weiqiang Wang, Xiaolin Zheng, Jianwei Yin,
• Abstract summary: 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'
• Score: 70.81375125791979
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: As a practical privacy-preserving learning method, split learning has drawn much attention in academia and industry. However, its security is constantly being questioned since the intermediate results are shared during training and inference. In this paper, we focus on the privacy leakage from the forward embeddings of split learning. Specifically, since the forward embeddings contain too much information about the label, the attacker can either use a few labeled samples to fine-tune the top model or perform unsupervised attacks such as clustering to infer the true labels from the forward embeddings. To prevent such kind of privacy leakage, we propose the potential energy loss to make the forward embeddings become more 'complicated', by pushing embeddings of the same class towards the decision boundary. Therefore, it is hard for the attacker to learn from the forward embeddings. Experiment results show that our method significantly lowers the performance of both fine-tuning attacks and clustering attacks.

Related papers

• Defending Label Inference Attacks in Split Learning under Regression Setting [20.77178463903939]
  Split Learning is a privacy-preserving method for implementing Vertical Federated Learning. In this paper, we focus on label inference attacks in Split Learning under regression setting. We propose Random Label Extension (RLE), where labels are extended to obfuscate the label information contained in the gradients. To further minimize the impact on the original task, we propose Model-based adaptive Label Extension (MLE), where original labels are preserved in the extended labels and dominate the training process.
  arXiv  Detail & Related papers  (2023-08-18T10:22:31Z)
• Students Parrot Their Teachers: Membership Inference on Model Distillation [54.392069096234074]
  We study the privacy provided by knowledge distillation to both the teacher and student training sets. Our attacks are strongest when student and teacher sets are similar, or when the attacker can poison the teacher set.
  arXiv  Detail & Related papers  (2023-03-06T19:16:23Z)
• Towards A Conceptually Simple Defensive Approach for Few-shot classifiers Against Adversarial Support Samples [107.38834819682315]
  We study a conceptually simple approach to defend few-shot classifiers against adversarial attacks. We propose a simple attack-agnostic detection method, using the concept of self-similarity and filtering. Our evaluation on the miniImagenet (MI) and CUB datasets exhibit good attack detection performance.
  arXiv  Detail & Related papers  (2021-10-24T05:46:03Z)
• Where Did You Learn That From? Surprising Effectiveness of Membership Inference Attacks Against Temporally Correlated Data in Deep Reinforcement Learning [114.9857000195174]
  A major challenge to widespread industrial adoption of deep reinforcement learning is the potential vulnerability to privacy breaches. We propose an adversarial attack framework tailored for testing the vulnerability of deep reinforcement learning algorithms to membership inference attacks.
  arXiv  Detail & Related papers  (2021-09-08T23:44:57Z)
• 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)
• Label Leakage and Protection in Two-party Split Learning [31.55902526103684]
  In this paper, we consider answering the question in an imbalanced binary classification setting. We first show that, norm attack, a simple method that uses the norm of the communicated gradients between the parties, can largely reveal the ground-truth labels from the participants. Among them, we have designed a principled approach that directly maximizes the worst-case error of label detection.
  arXiv  Detail & Related papers  (2021-02-17T00:01:49Z)
• Curse or Redemption? How Data Heterogeneity Affects the Robustness of Federated Learning [51.15273664903583]
  Data heterogeneity has been identified as one of the key features in federated learning but often overlooked in the lens of robustness to adversarial attacks. This paper focuses on characterizing and understanding its impact on backdooring attacks in federated learning through comprehensive experiments using synthetic and the LEAF benchmarks.
  arXiv  Detail & Related papers  (2021-02-01T06:06:21Z)
• Unleashing the Tiger: Inference Attacks on Split Learning [2.492607582091531]
  We introduce general attack strategies targeting the reconstruction of clients' private training sets. A malicious server can actively hijack the learning process of the distributed model. We demonstrate our attack is able to overcome recently proposed defensive techniques.
  arXiv  Detail & Related papers  (2020-12-04T15:41:00Z)
• 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.