Evading Data Provenance in Deep Neural Networks

• URL: http://arxiv.org/abs/2508.01074v1
• Date: Fri, 01 Aug 2025 21:13:45 GMT
• Title: Evading Data Provenance in Deep Neural Networks
• Authors: Hongyu Zhu, Sichu Liang, Wenwen Wang, Zhuomeng Zhang, Fangqi Li, Shi-Lin Wang,
• Abstract summary: We introduce a unified evasion framework, in which a teacher model first learns from the copyright dataset and then transfers task-relevant yet identifier-independent domain knowledge to a surrogate student.<n>Our approach simultaneously eliminates all copyright identifiers and significantly outperforms nine state-of-the-art evasion attacks in both generalization and effectiveness.<n>As a proof of concept, we reveal key vulnerabilities in current DOV methods, highlighting the need for long-term development to enhance practicality.
• Score: 15.428092329709823
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern over-parameterized deep models are highly data-dependent, with large scale general-purpose and domain-specific datasets serving as the bedrock for rapid advancements. However, many datasets are proprietary or contain sensitive information, making unrestricted model training problematic. In the open world where data thefts cannot be fully prevented, Dataset Ownership Verification (DOV) has emerged as a promising method to protect copyright by detecting unauthorized model training and tracing illicit activities. Due to its diversity and superior stealth, evading DOV is considered extremely challenging. However, this paper identifies that previous studies have relied on oversimplistic evasion attacks for evaluation, leading to a false sense of security. We introduce a unified evasion framework, in which a teacher model first learns from the copyright dataset and then transfers task-relevant yet identifier-independent domain knowledge to a surrogate student using an out-of-distribution (OOD) dataset as the intermediary. Leveraging Vision-Language Models and Large Language Models, we curate the most informative and reliable subsets from the OOD gallery set as the final transfer set, and propose selectively transferring task-oriented knowledge to achieve a better trade-off between generalization and evasion effectiveness. Experiments across diverse datasets covering eleven DOV methods demonstrate our approach simultaneously eliminates all copyright identifiers and significantly outperforms nine state-of-the-art evasion attacks in both generalization and effectiveness, with moderate computational overhead. As a proof of concept, we reveal key vulnerabilities in current DOV methods, highlighting the need for long-term development to enhance practicality.

Related papers

• DATABench: Evaluating Dataset Auditing in Deep Learning from an Adversarial Perspective [59.66984417026933]
  We introduce a novel taxonomy, classifying existing methods based on their reliance on internal features (IF) (inherent to the data) versus external features (EF) (artificially introduced for auditing)<n>We formulate two primary attack types: evasion attacks, designed to conceal the use of a dataset, and forgery attacks, intending to falsely implicate an unused dataset.<n>Building on the understanding of existing methods and attack objectives, we further propose systematic attack strategies: decoupling, removal, and detection for evasion; adversarial example-based methods for forgery.<n>Our benchmark, DATABench, comprises 17 evasion attacks, 5 forgery attacks, and 9
  arXiv  Detail & Related papers  (2025-07-08T03:07:15Z)
• Model Stealing Attack against Graph Classification with Authenticity, Uncertainty and Diversity [80.16488817177182]
  GNNs are vulnerable to the model stealing attack, a nefarious endeavor geared towards duplicating the target model via query permissions. We introduce three model stealing attacks to adapt to different actual scenarios.
  arXiv  Detail & Related papers  (2023-12-18T05:42:31Z)
• Combining inherent knowledge of vision-language models with unsupervised domain adaptation through strong-weak guidance [44.1830188215271]
  Unsupervised domain adaptation (UDA) tries to overcome the tedious work of labeling data by leveraging a labeled source dataset.<n>Current vision-language models exhibit remarkable zero-shot prediction capabilities.<n>We introduce a strong-weak guidance learning scheme that employs zero-shot predictions to help align the source and target dataset.
  arXiv  Detail & Related papers  (2023-12-07T06:16:39Z)
• DAD++: Improved Data-free Test Time Adversarial Defense [12.606555446261668]
  We propose a test time Data-free Adversarial Defense (DAD) containing detection and correction frameworks. We conduct a wide range of experiments and ablations on several datasets and network architectures to show the efficacy of our proposed approach. Our DAD++ gives an impressive performance against various adversarial attacks with a minimal drop in clean accuracy.
  arXiv  Detail & Related papers  (2023-09-10T20:39:53Z)
• Enhancing Multiple Reliability Measures via Nuisance-extended Information Bottleneck [77.37409441129995]
  In practical scenarios where training data is limited, many predictive signals in the data can be rather from some biases in data acquisition. We consider an adversarial threat model under a mutual information constraint to cover a wider class of perturbations in training. We propose an autoencoder-based training to implement the objective, as well as practical encoder designs to facilitate the proposed hybrid discriminative-generative training.
  arXiv  Detail & Related papers  (2023-03-24T16:03:21Z)
• Cluster-level pseudo-labelling for source-free cross-domain facial expression recognition [94.56304526014875]
  We propose the first Source-Free Unsupervised Domain Adaptation (SFUDA) method for Facial Expression Recognition (FER) Our method exploits self-supervised pretraining to learn good feature representations from the target data. We validate the effectiveness of our method in four adaptation setups, proving that it consistently outperforms existing SFUDA methods when applied to FER.
  arXiv  Detail & Related papers  (2022-10-11T08:24:50Z)
• 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)
• Hybrid Generative-Contrastive Representation Learning [32.84066504783469]
  We show that a transformer-based encoder-decoder architecture trained with both contrastive and generative losses can learn highly discriminative and robust representations without hurting the generative performance.
  arXiv  Detail & Related papers  (2021-06-11T04:23:48Z)
• Source Data-absent Unsupervised Domain Adaptation through Hypothesis Transfer and Labeling Transfer [137.36099660616975]
  Unsupervised adaptation adaptation (UDA) aims to transfer knowledge from a related but different well-labeled source domain to a new unlabeled target domain. Most existing UDA methods require access to the source data, and thus are not applicable when the data are confidential and not shareable due to privacy concerns. This paper aims to tackle a realistic setting with only a classification model available trained over, instead of accessing to the source data.
  arXiv  Detail & Related papers  (2020-12-14T07:28:50Z)
• SPEED: Secure, PrivatE, and Efficient Deep learning [2.283665431721732]
  We introduce a deep learning framework able to deal with strong privacy constraints. Based on collaborative learning, differential privacy and homomorphic encryption, the proposed approach advances state-of-the-art.
  arXiv  Detail & Related papers  (2020-06-16T19:31:52Z)

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.