mlsanityData to 14 Oct 2026

HoneyImage: Verifiable, Harmless, and Stealthy Dataset Ownership Verification for Image Models

arXiv 2508.00892 ↗First posted 27 Jul 2025cs.CV cs.AIcited by 0

On the map: LLM safety and security → Watermarking generated content and models

Abstract (arXiv)

Image-based AI models are increasingly deployed across a wide range of domains, including healthcare, security, and consumer applications. However, many image datasets carry sensitive or proprietary content, raising critical concerns about unauthorized data usage. Data owners therefore need reliable mechanisms to verify whether their proprietary data has been misused to train third-party models. Existing solutions, such as backdoor watermarking and membership inference, face inherent trade-offs between verification effectiveness and preservation of data integrity. In this work, we propose HoneyImage, a novel method for dataset ownership verification in image recognition models. HoneyImage selectively modifies a small number of hard samples to embed imperceptible yet verifiable traces, enabling reliable ownership verification while maintaining dataset integrity. Extensive experiments across four benchmark datasets and multiple model architectures show that HoneyImage consistently achieves strong verification accuracy with minimal impact on downstream performance while maintaining imperceptible. The proposed HoneyImage method could provide data owners with a practical mechanism to protect ownership over valuable image datasets, encouraging safe sharing and unlocking the full transformative potential of data-driven AI.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Watermarking generated content and models, one of 12 directions in LLM safety and security. Builds on 26 of its 57 references that are in the map. First posted on arXiv 27 Jul 2025.

Builds on

26 of 57 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  5. 2016Densely Connected Convolutional Networkscited by 6,720
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  7. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,183
  8. 2016Wide Residual Networkscited by 3,070
  9. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,281
  10. 2017EuroSAT: A Novel Dataset and Deep Learning Benchmark for Land Use and Land Cover Classificationcited by 1,496
  11. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,106
  12. 2017Targeted Backdoor Attacks on Deep Learning Systems Using Data Poisoningcited by 1,055
14 more
  1. 2021Membership Inference Attacks From First Principlescited by 878
  2. 2016Training Region-based Object Detectors with Online Hard Example Miningcited by 579
  3. 2020Systematic Evaluation of Privacy Risks of Machine Learning Modelscited by 292
  4. 2019White-box vs Black-box: Bayes Optimal Strategies for Membership Inferencecited by 271
  5. 2016Skin Lesion Analysis toward Melanoma Detection: A Challenge at the International Symposium on Biomedical Imaging (ISBI) 2016, hosted by the International Skin Imaging Collaboration (ISIC)cited by 198
  6. 2019Stolen Memories: Leveraging Model Memorization for Calibrated White-Box Membership Inferencecited by 175
  7. 2019Privacy Risks of Securing Machine Learning Models against Adversarial Examplescited by 141
  8. 2021Dataset Inference: Ownership Resolution in Machine Learningcited by 116
  9. 2019Multimodal End-to-End Autonomous Drivingcited by 110
  10. 2022Untargeted Backdoor Watermark: Towards Harmless and Stealthy Dataset Copyright Protectioncited by 86
  11. 2022Black-box Dataset Ownership Verification via Backdoor Watermarkingcited by 65
  12. 2016CNN Image Retrieval Learns from BoW: Unsupervised Fine-Tuning with Hard Examplescited by 58
  13. 2023Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Handcited by 57
  14. 2023Did You Train on My Dataset? Towards Public Dataset Protection with Clean-Label Backdoor Watermarkingcited by 37

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Data Taggants: Dataset Ownership Verification via Harmless Targeted Data Poisoning
  2. 2025CertDW: Towards Certified Dataset Ownership Verification via Conformal Calibration
  3. 2022On the Effectiveness of Dataset Watermarking in Adversarial Settings
  4. 2022On the Robustness of Dataset Inference
  5. 2025Towards Dataset Copyright Evasion Attack against Personalized Text-to-Image Diffusion Models
  6. 2024Revisiting Black-Box Model Ownership Verification through Information Theory
  7. 2026Membership is Ownership: A Robust Ownership Verification Framework for Diffusion Models
  8. 2024Generative Models are Self-Watermarked: Declaring Model Authentication through Re-Generation