Reconstructing Training Data From Real World Models Trained with Transfer Learning (2407.15845v1)
Abstract: Current methods for reconstructing training data from trained classifiers are restricted to very small models, limited training set sizes, and low-resolution images. Such restrictions hinder their applicability to real-world scenarios. In this paper, we present a novel approach enabling data reconstruction in realistic settings for models trained on high-resolution images. Our method adapts the reconstruction scheme of arXiv:2206.07758 to real-world scenarios -- specifically, targeting models trained via transfer learning over image embeddings of large pre-trained models like DINO-ViT and CLIP. Our work employs data reconstruction in the embedding space rather than in the image space, showcasing its applicability beyond visual data. Moreover, we introduce a novel clustering-based method to identify good reconstructions from thousands of candidates. This significantly improves on previous works that relied on knowledge of the training set to identify good reconstructed images. Our findings shed light on a potential privacy risk for data leakage from models trained using transfer learning.
- L. Biewald. Experiment tracking with weights and biases, 2020. URL https://www.wandb.com/. Software available from wandb.com.
- Food-101–mining discriminative components with random forests. In Computer Vision–ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6-12, 2014, Proceedings, Part VI 13, pages 446–461. Springer, 2014.
- Deconstructing data reconstruction: Multiclass, weight decay and general losses. In Advances in Neural Information Processing Systems, volume 36, pages 51515–51535, 2023.
- The secret sharer: Evaluating and testing unintended memorization in neural networks. In 28th USENIX Security Symposium (USENIX Security 19), pages 267–284, 2019.
- Extracting training data from large language models. In 30th USENIX Security Symposium (USENIX Security 21), pages 2633–2650, 2021.
- Extracting training data from diffusion models. arXiv preprint arXiv:2301.13188, 2023.
- Emerging properties in self-supervised vision transformers. In Proceedings of the IEEE/CVF international conference on computer vision, pages 9650–9660, 2021.
- Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition, pages 248–255. Ieee, 2009.
- An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929, 2020.
- Model inversion attacks that exploit confidence information and basic countermeasures. In Proceedings of the 22nd ACM SIGSAC conference on computer and communications security, pages 1322–1333, 2015.
- Inverting gradients-how easy is it to break privacy in federated learning? Advances in Neural Information Processing Systems, 33:16937–16947, 2020.
- Reconstructing training data from trained neural networks. NeurIPS, 2022.
- Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16000–16009, 2022.
- Model inversion attacks against collaborative inference. In Proceedings of the 35th Annual Computer Security Applications Conference, pages 148–162, 2019.
- Deep models under the gan: information leakage from collaborative deep learning. In Proceedings of the 2017 ACM SIGSAC conference on computer and communications security, pages 603–618, 2017.
- Evaluating gradient inversion attacks and defenses in federated learning. Advances in Neural Information Processing Systems, 34:7232–7241, 2021.
- A review of deep transfer learning and recent advancements. Technologies, 11(2):40, 2023.
- Z. Ji and M. Telgarsky. Directional convergence and alignment in deep learning. Advances in Neural Information Processing Systems, 33:17176–17186, 2020.
- Transfer learning for medical image classification: a literature review. BMC medical imaging, 22(1):69, 2022.
- Karlo-v1.0.alpha on coyo-100m and cc15m. https://github.com/kakaobrain/karlo, 2022.
- Dataset distillation fixes dataset reconstruction attacks. arXiv preprint arXiv:2302.01428, 2023.
- K. Lyu and J. Li. Gradient descent maximizes the margin of homogeneous neural networks. arXiv preprint arXiv:1906.05890, 2019.
- A. Mahendran and A. Vedaldi. Visualizing deep convolutional neural networks using natural pre-images. International Journal of Computer Vision, 120:233–255, 2016.
- Scalable extraction of training data from (production) language models. arXiv preprint arXiv:2311.17035, 2023.
- Learning and transferring mid-level image representations using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 1717–1724, 2014.
- Dinov2: Learning robust visual features without supervision. arXiv preprint arXiv:2304.07193, 2023.
- Pytorch: An imperative style, high-performance deep learning library. Advances in neural information processing systems, 32, 2019.
- Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. PMLR, 2021.
- Hierarchical text-conditional image generation with clip latents. arXiv preprint arXiv:2204.06125, 1(2):3, 2022.
- U-net: Convolutional networks for biomedical image segmentation. In Medical image computing and computer-assisted intervention–MICCAI 2015: 18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18, pages 234–241. Springer, 2015.
- K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556, 2014.
- Diffusion art or digital forgery? investigating data replication in diffusion models. arXiv preprint arXiv:2212.03860, 2022.
- A survey on deep transfer learning. In Artificial Neural Networks and Machine Learning–ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part III 27, pages 270–279. Springer, 2018.
- Splicing vit features for semantic appearance transfer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 10748–10757, 2022.
- Deep image prior. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 9446–9454, 2018.
- The inaturalist species classification and detection dataset. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8769–8778, 2018.
- Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, 13(4):600–612, 2004.
- Fishing for user data in large-batch federated learning via gradient magnification. arXiv preprint arXiv:2202.00580, 2022.
- R. Wightman. Pytorch image models. https://github.com/rwightman/pytorch-image-models, 2019.
- Neural network inversion in adversarial setting via background knowledge alignment. In Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security, pages 225–240, 2019.
- How transferable are features in deep neural networks? Advances in neural information processing systems, 27, 2014.
- The unreasonable effectiveness of deep features as a perceptual metric. In CVPR, 2018.
- Deep leakage from gradients. Advances in Neural Information Processing Systems, 32, 2019.
- A comprehensive survey on transfer learning. Proceedings of the IEEE, 109(1):43–76, 2020.