A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability

• URL: http://arxiv.org/abs/2505.10351v1
• Date: Thu, 15 May 2025 14:43:34 GMT
• Title: A Unified and Scalable Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability
• Authors: Jie Zhu, Jirong Zha, Ding Li, Leye Wang,
• Abstract summary: Self-supervised learning confronts significant privacy concerns, especially in vision.<n>In this paper, we perform membership inference on visual self-supervised models in a more realistic setting.<n>We propose a unified membership inference method called PartCrop.
• Score: 10.79834380458689
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Self-supervised learning shows promise in harnessing extensive unlabeled data, but it also confronts significant privacy concerns, especially in vision. In this paper, we perform membership inference on visual self-supervised models in a more realistic setting: self-supervised training method and details are unknown for an adversary when attacking as he usually faces a black-box system in practice. In this setting, considering that self-supervised model could be trained by completely different self-supervised paradigms, e.g., masked image modeling and contrastive learning, with complex training details, we propose a unified membership inference method called PartCrop. It is motivated by the shared part-aware capability among models and stronger part response on the training data. Specifically, PartCrop crops parts of objects in an image to query responses within the image in representation space. We conduct extensive attacks on self-supervised models with different training protocols and structures using three widely used image datasets. The results verify the effectiveness and generalization of PartCrop. Moreover, to defend against PartCrop, we evaluate two common approaches, i.e., early stop and differential privacy, and propose a tailored method called shrinking crop scale range. The defense experiments indicate that all of them are effective. Finally, besides prototype testing on toy visual encoders and small-scale image datasets, we quantitatively study the impacts of scaling from both data and model aspects in a realistic scenario and propose a scalable PartCrop-v2 by introducing two structural improvements to PartCrop. Our code is at https://github.com/JiePKU/PartCrop.

Related papers

• A Unified Membership Inference Method for Visual Self-supervised Encoder via Part-aware Capability [10.79834380458689]
  Self-supervised learning confronts significant privacy concerns, especially in vision. We propose a unified membership inference method called PartCrop. We conduct extensive attacks on self-supervised models with different training protocols and structures. To defend against PartCrop, we evaluate two common approaches, i.e., early stop and differential privacy, and propose a tailored method called shrinking crop scale range.
  arXiv  Detail & Related papers  (2024-04-03T05:04:55Z)
• Heuristic Vision Pre-Training with Self-Supervised and Supervised Multi-Task Learning [0.0]
  We propose a novel pre-training framework by adopting both self-supervised and supervised visual pre-text tasks in a multi-task manner. Results show that our pre-trained models can deliver results on par with or better than state-of-the-art (SOTA) results on multiple visual tasks.
  arXiv  Detail & Related papers  (2023-10-11T14:06:04Z)
• MOCA: Self-supervised Representation Learning by Predicting Masked Online Codebook Assignments [72.6405488990753]
  Self-supervised learning can be used for mitigating the greedy needs of Vision Transformer networks. We propose a single-stage and standalone method, MOCA, which unifies both desired properties. We achieve new state-of-the-art results on low-shot settings and strong experimental results in various evaluation protocols.
  arXiv  Detail & Related papers  (2023-07-18T15:46:20Z)
• Semantic-SAM: Segment and Recognize Anything at Any Granularity [83.64686655044765]
  We introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity. We consolidate multiple datasets across three granularities and introduce decoupled classification for objects and parts. For the multi-granularity capability, we propose a multi-choice learning scheme during training, enabling each click to generate masks at multiple levels.
  arXiv  Detail & Related papers  (2023-07-10T17:59:40Z)
• Understanding Self-Supervised Pretraining with Part-Aware Representation Learning [88.45460880824376]
  We study the capability that self-supervised representation pretraining methods learn part-aware representations. Results show that the fully-supervised model outperforms self-supervised models for object-level recognition.
  arXiv  Detail & Related papers  (2023-01-27T18:58:42Z)
• UniVIP: A Unified Framework for Self-Supervised Visual Pre-training [50.87603616476038]
  We propose a novel self-supervised framework to learn versatile visual representations on either single-centric-object or non-iconic dataset. Massive experiments show that UniVIP pre-trained on non-iconic COCO achieves state-of-the-art transfer performance. Our method can also exploit single-centric-object dataset such as ImageNet and outperforms BYOL by 2.5% with the same pre-training epochs in linear probing.
  arXiv  Detail & Related papers  (2022-03-14T10:04:04Z)
• Unsupervised Part Discovery from Contrastive Reconstruction [90.88501867321573]
  The goal of self-supervised visual representation learning is to learn strong, transferable image representations. We propose an unsupervised approach to object part discovery and segmentation. Our method yields semantic parts consistent across fine-grained but visually distinct categories.
  arXiv  Detail & Related papers  (2021-11-11T17:59:42Z)
• Multimodal Contrastive Training for Visual Representation Learning [45.94662252627284]
  We develop an approach to learning visual representations that embraces multimodal data. Our method exploits intrinsic data properties within each modality and semantic information from cross-modal correlation simultaneously. By including multimodal training in a unified framework, our method can learn more powerful and generic visual features.
  arXiv  Detail & Related papers  (2021-04-26T19:23:36Z)
• Self-supervised Human Detection and Segmentation via Multi-view Consensus [116.92405645348185]
  We propose a multi-camera framework in which geometric constraints are embedded in the form of multi-view consistency during training. We show that our approach outperforms state-of-the-art self-supervised person detection and segmentation techniques on images that visually depart from those of standard benchmarks.
  arXiv  Detail & Related papers  (2020-12-09T15:47:21Z)
• Learning View-Disentangled Human Pose Representation by Contrastive Cross-View Mutual Information Maximization [33.36330493757669]
  We introduce a novel representation learning method to disentangle pose-dependent as well as view-dependent factors from 2D human poses. The method trains a network using cross-view mutual information (CV-MIM) which maximizes mutual information of the same pose performed from different viewpoints. CV-MIM outperforms other competing methods by a large margin in the single-shot cross-view setting.
  arXiv  Detail & Related papers  (2020-12-02T18:55:35Z)

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.