# Bilateral Dependency Optimization: Defending Against Model-inversion Attacks

arXiv: https://arxiv.org/abs/2206.05483 · HTML: https://mlsanity.com/paper/2206.05483/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 43 references that are in the map.
- First posted on arXiv 11 Jun 2022.

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Analyzing and Improving the Image Quality of StyleGAN](https://mlsanity.com/paper/1912.04958/) (2019)
- [FaceNet: A Unified Embedding for Face Recognition and Clustering](https://mlsanity.com/paper/1503.03832/) (2015)
- [Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks](https://mlsanity.com/paper/1511.06434/) (2015)
- [Glow: Generative Flow with Invertible 1x1 Convolutions](https://mlsanity.com/paper/1807.03039/) (2018)
- [Label-Only Membership Inference Attacks](https://mlsanity.com/paper/2007.14321/) (2020)
- [The Secret Revealer: Generative Model-Inversion Attacks Against Deep Neural Networks](https://mlsanity.com/paper/1911.07135/) (2019)
- [Information Leakage in Embedding Models](https://mlsanity.com/paper/2004.00053/) (2020)
- [Evaluating Gradient Inversion Attacks and Defenses in Federated Learning](https://mlsanity.com/paper/2112.00059/) (2021)
- [A Survey of Privacy Attacks in Machine Learning](https://mlsanity.com/paper/2007.07646/) (2020)
- [Thieves on Sesame Street! Model Extraction of BERT-based APIs](https://mlsanity.com/paper/1910.12366/) (2019)
- [Learning Deep Kernels for Non-Parametric Two-Sample Tests](https://mlsanity.com/paper/2002.09116/) (2020)
- [Updates-Leak: Data Set Inference and Reconstruction Attacks in Online Learning](https://mlsanity.com/paper/1904.01067/) (2019)
- [Dipole: Diagnosis Prediction in Healthcare via Attention-based Bidirectional Recurrent Neural Networks](https://mlsanity.com/paper/1706.05764/) (2017)
- [Self-Supervised Learning with Kernel Dependence Maximization](https://mlsanity.com/paper/2106.08320/) (2021)
- [Variational Model Inversion Attacks](https://mlsanity.com/paper/2201.10787/) (2022)
- [Knowledge-Enriched Distributional Model Inversion Attacks](https://mlsanity.com/paper/2010.04092/) (2020)
- [Improving Robustness to Model Inversion Attacks via Mutual Information Regularization](https://mlsanity.com/paper/2009.05241/) (2020)
- [Maximum Mean Discrepancy Test is Aware of Adversarial Attacks](https://mlsanity.com/paper/2010.11415/) (2020)
- [Defending Model Inversion and Membership Inference Attacks via Prediction Purification](https://mlsanity.com/paper/2005.03915/) (2020)
- [Adversarial Neural Network Inversion via Auxiliary Knowledge Alignment](https://mlsanity.com/paper/1902.08552/) (2019)
- [Meta Two-Sample Testing: Learning Kernels for Testing with Limited Data](https://mlsanity.com/paper/2106.07636/) (2021)

## Built on by (most cited first, 30 of 30)

- [Re-thinking Model Inversion Attacks Against Deep Neural Networks](https://mlsanity.com/paper/2304.01669/) (2023)
- [Quality-Agnostic Deepfake Detection with Intra-model Collaborative Learning](https://mlsanity.com/paper/2309.05911/) (2023)
- [Privacy Leakage on DNNs: A Survey of Model Inversion Attacks and Defenses](https://mlsanity.com/paper/2402.04013/) (2024)
- [Label-Only Model Inversion Attacks via Knowledge Transfer](https://mlsanity.com/paper/2310.19342/) (2023)
- [A Closer Look at GAN Priors: Exploiting Intermediate Features for Enhanced Model Inversion Attacks](https://mlsanity.com/paper/2407.13863/) (2024)
- [On Strengthening and Defending Graph Reconstruction Attack with Markov Chain Approximation](https://mlsanity.com/paper/2306.09104/) (2023)
- [Unstoppable Attack: Label-Only Model Inversion via Conditional Diffusion Model](https://mlsanity.com/paper/2307.08424/) (2023)
- [Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks](https://mlsanity.com/paper/2310.06549/) (2023)
- [Model Inversion Robustness: Can Transfer Learning Help?](https://mlsanity.com/paper/2405.05588/) (2024)
- [Model Inversion Attacks: A Survey of Approaches and Countermeasures](https://mlsanity.com/paper/2411.10023/) (2024)
- [Robust Spatiotemporal Traffic Forecasting with Reinforced Dynamic Adversarial Training](https://mlsanity.com/paper/2306.14126/) (2023)
- [On the Vulnerability of Skip Connections to Model Inversion Attacks](https://mlsanity.com/paper/2409.01696/) (2024)
- [Boosting Model Inversion Attacks with Adversarial Examples](https://mlsanity.com/paper/2306.13965/) (2023)
- [Improving Robustness to Model Inversion Attacks via Sparse Coding Architectures](https://mlsanity.com/paper/2403.14772/) (2024)
- [Model Inversion Attacks Through Target-Specific Conditional Diffusion Models](https://mlsanity.com/paper/2407.11424/) (2024)
- [Theoretical Insights in Model Inversion Robustness and Conditional Entropy Maximization for Collaborative Inference Systems](https://mlsanity.com/paper/2503.00383/) (2025)
- [MIBench: A Comprehensive Framework for Benchmarking Model Inversion Attack and Defense](https://mlsanity.com/paper/2410.05159/) (2024)
- [Trap-MID: Trapdoor-based Defense against Model Inversion Attacks](https://mlsanity.com/paper/2411.08460/) (2024)
- [Diversity-enhancing Generative Network for Few-shot Hypothesis Adaptation](https://mlsanity.com/paper/2307.05948/) (2023)
- [Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering](https://mlsanity.com/paper/2410.05814/) (2024)
- [Random Erasing vs. Model Inversion: A Promising Defense or a False Hope?](https://mlsanity.com/paper/2409.01062/) (2024)
- [Revisiting Model Inversion Evaluation: From Misleading Standards to Reliable Privacy Assessment](https://mlsanity.com/paper/2505.03519/) (2025)
- [Generative Model Inversion Through the Lens of the Manifold Hypothesis](https://mlsanity.com/paper/2509.20177/) (2025)
- [AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective](https://mlsanity.com/paper/2603.24857/) (2026)
- [Defending Against Gradient Inversion Attacks for Biomedical Images via Learnable Data Perturbation](https://mlsanity.com/paper/2503.16542/) (2025)
- [Do Vision-Language Models Leak What They Learn? Adaptive Token-Weighted Model Inversion Attacks](https://mlsanity.com/paper/2508.04097/) (2025)
- [Model Inversion meets Cryptographic Fuzzy Extractors](https://mlsanity.com/paper/2510.25687/) (2025)
- [Reducing information dependency does not cause training data privacy. Adversarially non-robust features do](https://mlsanity.com/paper/2607.12354/) (2026)
- [Steering the Flow: Inverting Face Recognition Models via Gradient-Guided Flow Matching](https://mlsanity.com/paper/2608.16791/) (2026)
- [On the Relationship between Model Quantization and Model Inversion Attacks](https://mlsanity.com/paper/2610.00382/) (2026)

## Abstract (arXiv)

Through using only a well-trained classifier, model-inversion (MI) attacks can recover the data used for training the classifier, leading to the privacy leakage of the training data. To defend against MI attacks, previous work utilizes a unilateral dependency optimization strategy, i.e., minimizing the dependency between inputs (i.e., features) and outputs (i.e., labels) during training the classifier. However, such a minimization process conflicts with minimizing the supervised loss that aims to maximize the dependency between inputs and outputs, causing an explicit trade-off between model robustness against MI attacks and model utility on classification tasks. In this paper, we aim to minimize the dependency between the latent representations and the inputs while maximizing the dependency between latent representations and the outputs, named a bilateral dependency optimization (BiDO) strategy. In particular, we use the dependency constraints as a universally applicable regularizer in addition to commonly used losses for deep neural networks (e.g., cross-entropy), which can be instantiated with appropriate dependency criteria according to different tasks. To verify the efficacy of our strategy, we propose two implementations of BiDO, by using two different dependency measures: BiDO with constrained covariance (BiDO-COCO) and BiDO with Hilbert-Schmidt Independence Criterion (BiDO-HSIC). Experiments show that BiDO achieves the state-of-the-art defense performance for a variety of datasets, classifiers, and MI attacks while suffering a minor classification-accuracy drop compared to the well-trained classifier with no defense, which lights up a novel road to defend against MI attacks.