Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection

• URL: http://arxiv.org/abs/2210.00875v3
• Date: Wed, 5 Apr 2023 13:32:57 GMT
• Title: Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protection
• Authors: Yiming Li, Yang Bai, Yong Jiang, Yong Yang, Shu-Tao Xia, Bo Li
• Abstract summary: We explore the untargeted backdoor watermarking scheme, where the abnormal model behaviors are not deterministic. We also discuss how to use the proposed untargeted backdoor watermark for dataset ownership verification.
• Score: 69.59980270078067
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Deep neural networks (DNNs) have demonstrated their superiority in practice. Arguably, the rapid development of DNNs is largely benefited from high-quality (open-sourced) datasets, based on which researchers and developers can easily evaluate and improve their learning methods. Since the data collection is usually time-consuming or even expensive, how to protect their copyrights is of great significance and worth further exploration. In this paper, we revisit dataset ownership verification. We find that existing verification methods introduced new security risks in DNNs trained on the protected dataset, due to the targeted nature of poison-only backdoor watermarks. To alleviate this problem, in this work, we explore the untargeted backdoor watermarking scheme, where the abnormal model behaviors are not deterministic. Specifically, we introduce two dispersibilities and prove their correlation, based on which we design the untargeted backdoor watermark under both poisoned-label and clean-label settings. We also discuss how to use the proposed untargeted backdoor watermark for dataset ownership verification. Experiments on benchmark datasets verify the effectiveness of our methods and their resistance to existing backdoor defenses. Our codes are available at \url{https://github.com/THUYimingLi/Untargeted_Backdoor_Watermark}.

Related papers

• PointNCBW: Towards Dataset Ownership Verification for Point Clouds via Negative Clean-label Backdoor Watermark [20.746346834429925]
  We propose a clean-label backdoor-based dataset watermark for point clouds that ensures both effectiveness and stealthiness. We perturb selected point clouds with non-target categories in both shape-wise and point-wise manners before inserting trigger patterns. As such, models trained on the watermarked dataset will have a distinctive yet stealthy backdoor behavior.
  arXiv  Detail & Related papers  (2024-08-10T09:31:58Z)
• Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand [96.26251471253823]
  backdoor-based dataset ownership verification (DOV) is currently the only feasible approach to protect the copyright of open-source datasets. We make watermarked models (trained on the protected dataset) correctly classify some hard' samples that will be misclassified by the benign model.
  arXiv  Detail & Related papers  (2023-10-09T11:23:05Z)
• Towards Robust Model Watermark via Reducing Parametric Vulnerability [57.66709830576457]
  backdoor-based ownership verification becomes popular recently, in which the model owner can watermark the model. We propose a mini-max formulation to find these watermark-removed models and recover their watermark behavior. Our method improves the robustness of the model watermarking against parametric changes and numerous watermark-removal attacks.
  arXiv  Detail & Related papers  (2023-09-09T12:46:08Z)
• Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarking [54.40184736491652]
  We propose a backdoor-based watermarking approach that serves as a general framework for safeguarding public-available data. By inserting a small number of watermarking samples into the dataset, our approach enables the learning model to implicitly learn a secret function set by defenders. This hidden function can then be used as a watermark to track down third-party models that use the dataset illegally.
  arXiv  Detail & Related papers  (2023-03-20T21:54:30Z)
• 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)
• Black-box Dataset Ownership Verification via Backdoor Watermarking [67.69308278379957]
  We formulate the protection of released datasets as verifying whether they are adopted for training a (suspicious) third-party model. We propose to embed external patterns via backdoor watermarking for the ownership verification to protect them. Specifically, we exploit poison-only backdoor attacks ($e.g.$, BadNets) for dataset watermarking and design a hypothesis-test-guided method for dataset verification.
  arXiv  Detail & Related papers  (2022-08-04T05:32:20Z)
• Detect and remove watermark in deep neural networks via generative adversarial networks [10.058070050660104]
  We propose a scheme to detect and remove watermark in deep neural networks via generative adversarial networks (GAN) In the first phase, we use the GAN and few clean images to detect and reverse the watermark in the DNN model. In the second phase, we fine-tune the watermarked DNN based on the reversed backdoor images.
  arXiv  Detail & Related papers  (2021-06-15T12:45:22Z)
• Open-sourced Dataset Protection via Backdoor Watermarking [87.15630326131901]
  We propose a emphbackdoor embedding based dataset watermarking method to protect an open-sourced image-classification dataset. We use a hypothesis test guided method for dataset verification based on the posterior probability generated by the suspicious third-party model.
  arXiv  Detail & Related papers  (2020-10-12T16:16:27Z)

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.