mlsanityData to 7 Oct 2026

Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model's Complexity

arXiv 2104.13061 ↗First posted 27 Apr 2021cs.CR cs.LGcited by 19

Not on the map. Why?

Abstract (arXiv)

Machine learning models' goal is to make correct predictions for specific tasks by learning important properties and patterns from data. By doing so, there is a chance that the model learns properties that are unrelated to its primary task. Property Inference Attacks exploit this and aim to infer from a given model (ie the target model) properties about the training dataset seemingly unrelated to the model's primary goal. If the training data is sensitive, such an attack could lead to privacy leakage. This paper investigates the influence of the target model's complexity on the accuracy of this type of attack, focusing on convolutional neural network classifiers. We perform attacks on models that are trained on facial images to predict whether someone's mouth is open. Our attacks' goal is to infer whether the training dataset is balanced gender-wise. Our findings reveal that the risk of a privacy breach is present independently of the target model's complexity: for all studied architectures, the attack's accuracy is clearly over the baseline. We discuss the implication of the property inference on personal data in the light of Data Protection Regulations and Guidelines.

Key facts. Cited by 19 papers in the map (data through 7 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 27 Apr 2021.

Builds on

24 of 40 references.

References · 24

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  4. 2019Deep Leakage from Gradientscited by 1,004
  5. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  6. 2020Inverting Gradients -- How easy is it to break privacy in federated learning?cited by 707
  7. 2016Stealing Machine Learning Models via Prediction APIscited by 602
  8. 2018Exploiting Unintended Feature Leakage in Collaborative Learningcited by 509
  9. 2017Deep Models Under the GAN: Information Leakage from Collaborative Deep Learningcited by 326
  10. 2018Beyond Inferring Class Representatives: User-Level Privacy Leakage From Federated Learningcited by 242
  11. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  12. 2018Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learningcited by 219
12 more
  1. 2020A Survey of Privacy Attacks in Machine Learningcited by 143
  2. 2013Hacking Smart Machines with Smarter Ones: How to Extract Meaningful Data from Machine Learning Classifierscited by 128
  3. 2018Stealing Hyperparameters in Machine Learningcited by 115
  4. 2020Sponge Examples: Energy-Latency Attacks on Neural Networkscited by 108
  5. 2018Algorithms that Remember: Model Inversion Attacks and Data Protection Lawcited by 52
  6. 2018Explanation Methods in Deep Learning: Users, Values, Concerns and Challengescited by 49
  7. 2018Towards Demystifying Membership Inference Attackscited by 39
  8. 2019Eavesdrop the Composition Proportion of Training Labels in Federated Learningcited by 27
  9. 2019Quantification of the Leakage in Federated Learningcited by 7
  10. 2020Black-box Model Inversion Attribute Inference Attacks on Classification Modelscited by 6
  11. 2019Towards Security Threats of Deep Learning Systems: A Surveycited by 5
  12. 2019Quantifying the Privacy Risks of Learning High-Dimensional Graphical Modelscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 5; 2023: 5; 2024: 7; 2025: 0; 2026: 1.

19 papers.

Sort:

By area:

  1. 2023Bag of Tricks for Training Data Extraction from Language Modelscited by 67
  2. 2021Privacy-Preserving Machine Learning: Methods, Challenges and Directionscited by 58
  3. 2022A Comprehensive Survey on Trustworthy Recommender Systemscited by 32
  4. 2022Group Property Inference Attacks Against Graph Neural Networkscited by 21
  5. 2022PPA: Preference Profiling Attack Against Federated Learningcited by 8
  6. 2023Transpose Attack: Stealing Datasets with Bidirectional Trainingcited by 4
  7. 2024Can Graph Neural Networks Expose Training Data Properties? An Efficient Risk Assessment Approachcited by 3
  8. 2024Memory Backdoor Attacks on Neural Networkscited by 3
  9. 2023Class Attribute Inference Attacks: Inferring Sensitive Class Information by Diffusion-Based Attribute Manipulationscited by 2
  10. 2023MLHOps: Machine Learning for Healthcare Operationscited by 2
  11. 2024Inference Attacks: A Taxonomy, Survey, and Promising Directionscited by 2
  12. 2022Inferring Class Label Distribution of Training Data from Classifiers: An Accuracy-Augmented Meta-Classifier Attackcited by 1
7 more
  1. 2022Memorization of Named Entities in Fine-tuned BERT Modelscited by 1
  2. 2023Private Training Set Inspection in MLaaScited by 0
  3. 2024Security and Privacy Issues and Solutions in Federated Learning for Digital Healthcarecited by 0
  4. 2024Unraveling Attacks in Machine Learning-based IoT Ecosystems: A Survey and the Open Libraries Behind Themcited by 0
  5. 2024FRIDA: Free-Rider Detection using Privacy Attackscited by 0
  6. 2024Calibrating Practical Privacy Risks for Differentially Private Machine Learningcited by 0
  7. 2026Robust Federated Learning via Byzantine Filtering over Encrypted Updatescited by 0