Membership Inference Test: Auditing Training Data in Object Classification Models

• URL: http://arxiv.org/abs/2601.12929v1
• Date: Mon, 19 Jan 2026 10:30:53 GMT
• Title: Membership Inference Test: Auditing Training Data in Object Classification Models
• Authors: Gonzalo Mancera, Daniel DeAlcala, Aythami Morales, Ruben Tolosana, Julian Fierrez,
• Abstract summary: This research focuses on determining whether given data were utilized during the training phase, specifically in the domain of object recognition.<n>Within the area of object recognition, we propose and develop architectures tailored for MINT models.<n>These architectures aim to optimize performance and efficiency in data utilization, offering a tailored solution to tackle the complexities inherent in the object recognition domain.
• Score: 16.766968065779782
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: In this research, we analyze the performance of Membership Inference Tests (MINT), focusing on determining whether given data were utilized during the training phase, specifically in the domain of object recognition. Within the area of object recognition, we propose and develop architectures tailored for MINT models. These architectures aim to optimize performance and efficiency in data utilization, offering a tailored solution to tackle the complexities inherent in the object recognition domain. We conducted experiments involving an object detection model, an embedding extractor, and a MINT module. These experiments were performed in three public databases, totaling over 174K images. The proposed architecture leverages convolutional layers to capture and model the activation patterns present in the data during the training process. Through our analysis, we are able to identify given data used for testing and training, achieving precision rates ranging between 70% and 80%, contingent upon the depth of the detection module layer chosen for input to the MINT module. Additionally, our studies entail an analysis of the factors influencing the MINT Module, delving into the contributing elements behind more transparent training processes.

Related papers

• Enhancing Object Detection with Privileged Information: A Model-Agnostic Teacher-Student Approach [2.1303542744717148]
  This paper investigates the integration of the Learning Using Privileged Information (LUPI) paradigm in object detection.<n>We introduce a general, model-agnostic methodology for injecting privileged information-such as bounding box masks-into deep learning-based object detectors.
  arXiv  Detail & Related papers  (2026-01-05T11:24:34Z)
• Equipping Vision Foundation Model with Mixture of Experts for Out-of-Distribution Detection [36.97738113847375]
  We investigate representative vision foundation models for OOD detection.<n>A pre-trained DINOv2 model naturally provides a highly discriminative feature space for OOD detection.<n>Fine-tuning foundation models on in-domain (ID) data can enhance OOD detection.<n>We propose the Mixture of Feature Experts (MoFE) module, which partitions features into subspaces.
  arXiv  Detail & Related papers  (2025-10-12T13:00:53Z)
• Active Membership Inference Test (aMINT): Enhancing Model Auditability with Multi-Task Learning [18.552238031865286]
  Active Membership Inference Test (aMINT) is a method designed to detect whether given data were used during the training of machine learning models.<n>We propose a novel multitask learning process that involves training simultaneously two models.<n>We present results using a wide range of neural networks, from lighter architectures such as MobileNet to more complex ones such as Vision Transformers.
  arXiv  Detail & Related papers  (2025-09-09T16:00:03Z)
• Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs [14.618008816273784]
  MINT is a general approach to determine if given data was used for training machine learning models.<n>This work focuses on its application to the domain of Natural Language Processing.
  arXiv  Detail & Related papers  (2025-03-10T14:32:56Z)
• Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning [51.170479006249195]
  We introduce a new dataset, benchmark, and a dynamic coarse-to-fine learning scheme in this study.<n>Our proposed dataset, AI-TOD-R, features the smallest object sizes among all oriented object detection datasets.<n>We present a benchmark spanning a broad range of detection paradigms, including both fully-supervised and label-efficient approaches.
  arXiv  Detail & Related papers  (2024-12-16T09:14:32Z)
• iNNspector: Visual, Interactive Deep Model Debugging [8.997568393450768]
  We propose a conceptual framework structuring the data space of deep learning experiments. Our framework captures design dimensions and proposes mechanisms to make this data explorable and tractable. We present the iNNspector system, which enables tracking of deep learning experiments and provides interactive visualizations of the data.
  arXiv  Detail & Related papers  (2024-07-25T12:48:41Z)
• 3rd Place Solution for MOSE Track in CVPR 2024 PVUW workshop: Complex Video Object Segmentation [63.199793919573295]
  Video Object (VOS) is a vital task in computer vision, focusing on distinguishing foreground objects from the background across video frames. Our work draws inspiration from the Cutie model, and we investigate the effects of object memory, the total number of memory frames, and input resolution on segmentation performance.
  arXiv  Detail & Related papers  (2024-06-06T00:56:25Z)
• Innovative Horizons in Aerial Imagery: LSKNet Meets DiffusionDet for Advanced Object Detection [55.2480439325792]
  We present an in-depth evaluation of an object detection model that integrates the LSKNet backbone with the DiffusionDet head. The proposed model achieves a mean average precision (MAP) of approximately 45.7%, which is a significant improvement. This advancement underscores the effectiveness of the proposed modifications and sets a new benchmark in aerial image analysis.
  arXiv  Detail & Related papers  (2023-11-21T19:49:13Z)
• The Impact of Different Backbone Architecture on Autonomous Vehicle Dataset [120.08736654413637]
  The quality of the features extracted by the backbone architecture can have a significant impact on the overall detection performance. Our study evaluates three well-known autonomous vehicle datasets, namely KITTI, NuScenes, and BDD, to compare the performance of different backbone architectures on object detection tasks.
  arXiv  Detail & Related papers  (2023-09-15T17:32:15Z)
• Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
  Unsupervised object discovery is promising due to its ability to discover objects in a generic manner. We design a semantic-guided self-supervised learning model to extract high-level semantic features from images. We introduce Principal Component Analysis (PCA) to localize object regions.
  arXiv  Detail & Related papers  (2023-07-07T04:03:48Z)
• Information-Theoretic Odometry Learning [83.36195426897768]
  We propose a unified information theoretic framework for learning-motivated methods aimed at odometry estimation. The proposed framework provides an elegant tool for performance evaluation and understanding in information-theoretic language.
  arXiv  Detail & Related papers  (2022-03-11T02:37:35Z)

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.