mlsanityData to 7 Oct 2026

Transpose Attack: Stealing Datasets with Bidirectional Training

arXiv 2311.07389 ↗First posted 13 Nov 2023cs.LG cs.CRcited by 4

Not on the map. Why?

Abstract (arXiv)

Deep neural networks are normally executed in the forward direction. However, in this work, we identify a vulnerability that enables models to be trained in both directions and on different tasks. Adversaries can exploit this capability to hide rogue models within seemingly legitimate models. In addition, in this work we show that neural networks can be taught to systematically memorize and retrieve specific samples from datasets. Together, these findings expose a novel method in which adversaries can exfiltrate datasets from protected learning environments under the guise of legitimate models. We focus on the data exfiltration attack and show that modern architectures can be used to secretly exfiltrate tens of thousands of samples with high fidelity, high enough to compromise data privacy and even train new models. Moreover, to mitigate this threat we propose a novel approach for detecting infected models.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 34 of its 66 references that are in the map. First posted on arXiv 13 Nov 2023.

Builds on

34 of 66 references.

References · 34

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020Language Models are Few-Shot Learnerscited by 32,199
  4. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  5. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  6. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  7. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  8. 2020Extracting Training Data from Large Language Modelscited by 2,144
  9. 2016Adversarial examples in the physical worldcited by 1,762
  10. 2021VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learningcited by 1,013
  11. 2021Transformers in Vision: A Surveycited by 1,009
  12. 2019Deep Leakage from Gradientscited by 1,004
22 more
  1. 2023Extracting Training Data from Diffusion Modelscited by 723
  2. 2018Spectral Signatures in Backdoor Attackscited by 457
  3. 2018Detecting Backdoor Attacks on Deep Neural Networks by Activation Clusteringcited by 429
  4. 2020Backdoor Learning: A Surveycited by 412
  5. 2016Tutorial on Variational Autoencoderscited by 404
  6. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  7. 2017Lossy Image Compression with Compressive Autoencoderscited by 289
  8. 2019The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networkscited by 241
  9. 2022Reconstructing Training Data from Trained Neural Networkscited by 129
  10. 2021Data Collection and Quality Challenges in Deep Learning: A Data-Centric AI Perspectivecited by 116
  11. 2022Truth Serum: Poisoning Machine Learning Models to Reveal Their Secretscited by 94
  12. 2021Aggregated Contextual Transformations for High-Resolution Image Inpaintingcited by 89
  13. 2021Black-box Detection of Backdoor Attacks with Limited Information and Datacited by 71
  14. 2018Algorithms that Remember: Model Inversion Attacks and Data Protection Lawcited by 52
  15. 2021Formalizing and Estimating Distribution Inference Riskscited by 42
  16. 2019Gotta Catch 'Em All: Using Honeypots to Catch Adversarial Attacks on Neural Networkscited by 40
  17. 2022A Survey on Gradient Inversion: Attacks, Defenses and Future Directionscited by 39
  18. 2021Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model's Complexitycited by 19
  19. 2021EvilModel: Hiding Malware Inside of Neural Network Modelscited by 15
  20. 2016A Survey of Credit Card Fraud Detection Techniques: Data and Technique Oriented Perspectivecited by 8
  21. 2020On Hiding Neural Networks Inside Neural Networkscited by 2
  22. 2022Data Stealing Attack on Medical Images: Is it Safe to Export Networks from Data Lakes?cited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2024Memory Backdoor Attacks on Neural Networkscited by 3
  2. 2025Mitigating Data Exfiltration Attacks through Layer-Wise Learning Rate Decay Fine-Tuningcited by 1
  3. 2024Model X-Ray: Detection of Hidden Malware in AI Model Weights using Few Shot Learningcited by 0
  4. 2026High-Capacity Robust Medical Image Exfiltration via Neural Network Weight Replacementcited by 0