INK: Inheritable Natural Backdoor Attack Against Model Distillation

• URL: http://arxiv.org/abs/2304.10985v3
• Date: Mon, 9 Sep 2024 03:19:10 GMT
• Title: INK: Inheritable Natural Backdoor Attack Against Model Distillation
• Authors: Xiaolei Liu, Ming Yi, Kangyi Ding, Bangzhou Xin, Yixiao Xu, Li Yan, Chao Shen,
• Abstract summary: We introduce INK, an inheritable natural backdoor attack that targets model distillation. INK employs image variance as a backdoor trigger and enables both clean-image and clean-label attacks. For instance, INK maintains an attack success rate of over 98% post-distillation, compared to an average success rate of 1.4% for existing methods.
• Score: 8.937026844871074
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Deep learning models are vulnerable to backdoor attacks, where attackers inject malicious behavior through data poisoning and later exploit triggers to manipulate deployed models. To improve the stealth and effectiveness of backdoors, prior studies have introduced various imperceptible attack methods targeting both defense mechanisms and manual inspection. However, all poisoning-based attacks still rely on privileged access to the training dataset. Consequently, model distillation using a trusted dataset has emerged as an effective defense against these attacks. To bridge this gap, we introduce INK, an inheritable natural backdoor attack that targets model distillation. The key insight behind INK is the use of naturally occurring statistical features in all datasets, allowing attackers to leverage them as backdoor triggers without direct access to the training data. Specifically, INK employs image variance as a backdoor trigger and enables both clean-image and clean-label attacks by manipulating the labels and image variance in an unauthenticated dataset. Once the backdoor is embedded, it transfers from the teacher model to the student model, even when defenders use a trusted dataset for distillation. Theoretical analysis and experimental results demonstrate the robustness of INK against transformation-based, search-based, and distillation-based defenses. For instance, INK maintains an attack success rate of over 98\% post-distillation, compared to an average success rate of 1.4\% for existing methods.

Related papers

• DMGNN: Detecting and Mitigating Backdoor Attacks in Graph Neural Networks [30.766013737094532]
  We propose DMGNN against out-of-distribution (OOD) and in-distribution (ID) graph backdoor attacks. DMGNN can easily identify the hidden ID and OOD triggers via predicting label transitions based on counterfactual explanation. DMGNN far outperforms the state-of-the-art (SOTA) defense methods, reducing the attack success rate to 5% with almost negligible degradation in model performance.
  arXiv  Detail & Related papers  (2024-10-18T01:08:03Z)
• Long-Tailed Backdoor Attack Using Dynamic Data Augmentation Operations [50.1394620328318]
  Existing backdoor attacks mainly focus on balanced datasets. We propose an effective backdoor attack named Dynamic Data Augmentation Operation (D$2$AO) Our method can achieve the state-of-the-art attack performance while preserving the clean accuracy.
  arXiv  Detail & Related papers  (2024-10-16T18:44:22Z)
• Efficient Backdoor Defense in Multimodal Contrastive Learning: A Token-Level Unlearning Method for Mitigating Threats [52.94388672185062]
  We propose an efficient defense mechanism against backdoor threats using a concept known as machine unlearning. This entails strategically creating a small set of poisoned samples to aid the model's rapid unlearning of backdoor vulnerabilities. In the backdoor unlearning process, we present a novel token-based portion unlearning training regime.
  arXiv  Detail & Related papers  (2024-09-29T02:55:38Z)
• Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor [63.84477483795964]
  Data-poisoning backdoor attacks are serious security threats to machine learning models. In this paper, we focus on in-training backdoor defense, aiming to train a clean model even when the dataset may be potentially poisoned. We propose a novel defense approach called PDB (Proactive Defensive Backdoor)
  arXiv  Detail & Related papers  (2024-05-25T07:52:26Z)
• SEEP: Training Dynamics Grounds Latent Representation Search for Mitigating Backdoor Poisoning Attacks [53.28390057407576]
  Modern NLP models are often trained on public datasets drawn from diverse sources. Data poisoning attacks can manipulate the model's behavior in ways engineered by the attacker. Several strategies have been proposed to mitigate the risks associated with backdoor attacks.
  arXiv  Detail & Related papers  (2024-05-19T14:50:09Z)
• Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective [65.70799289211868]
  We introduce two new theory-driven trigger pattern generation methods specialized for dataset distillation. We show that our optimization-based trigger design framework informs effective backdoor attacks on dataset distillation.
  arXiv  Detail & Related papers  (2023-11-28T09:53:05Z)
• Backdoor Defense via Deconfounded Representation Learning [17.28760299048368]
  We propose a Causality-inspired Backdoor Defense (CBD) to learn deconfounded representations for reliable classification. CBD is effective in reducing backdoor threats while maintaining high accuracy in predicting benign samples.
  arXiv  Detail & Related papers  (2023-03-13T02:25:59Z)
• Invisible Backdoor Attacks Using Data Poisoning in the Frequency Domain [8.64369418938889]
  We propose a generalized backdoor attack method based on the frequency domain. It can implement backdoor implantation without mislabeling and accessing the training process. We evaluate our approach in the no-label and clean-label cases on three datasets.
  arXiv  Detail & Related papers  (2022-07-09T07:05:53Z)
• Model-Contrastive Learning for Backdoor Defense [13.781375023320981]
  We propose a novel backdoor defense method named MCL based on model-contrastive learning. MCL is more effective for reducing backdoor threats while maintaining higher accuracy of benign data.
  arXiv  Detail & Related papers  (2022-05-09T16:36:46Z)
• Narcissus: A Practical Clean-Label Backdoor Attack with Limited Information [22.98039177091884]
  "Clean-label" backdoor attacks require knowledge of the entire training set to be effective. This paper provides an algorithm to mount clean-label backdoor attacks based only on the knowledge of representative examples from the target class. Our attack works well across datasets and models, even when the trigger presents in the physical world.
  arXiv  Detail & Related papers  (2022-04-11T16:58:04Z)
• Black-box Detection of Backdoor Attacks with Limited Information and Data [56.0735480850555]
  We propose a black-box backdoor detection (B3D) method to identify backdoor attacks with only query access to the model. In addition to backdoor detection, we also propose a simple strategy for reliable predictions using the identified backdoored models.
  arXiv  Detail & Related papers  (2021-03-24T12:06:40Z)

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.