# Decoupling Generalizability and Membership Privacy Risks in Neural Networks

arXiv: https://arxiv.org/abs/2602.02296 · HTML: https://mlsanity.com/paper/2602.02296/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 59 references that are in the map.
- First posted on arXiv 2 Feb 2026.

## Builds on (most cited first, 30 of 43)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Adversarial Training for Free!](https://mlsanity.com/paper/1904.12843/) (2019)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Be Your Own Teacher: Improve the Performance of Convolutional Neural Networks via Self Distillation](https://mlsanity.com/paper/1905.08094/) (2019)
- [Label-Only Membership Inference Attacks](https://mlsanity.com/paper/2007.14321/) (2020)
- [Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations](https://mlsanity.com/paper/2204.02937/) (2022)
- [Systematic Evaluation of Privacy Risks of Machine Learning Models](https://mlsanity.com/paper/2003.10595/) (2020)
- [MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examples](https://mlsanity.com/paper/1909.10594/) (2019)
- [Machine Learning with Membership Privacy using Adversarial Regularization](https://mlsanity.com/paper/1807.05852/) (2018)
- [Regularizing Class-wise Predictions via Self-knowledge Distillation](https://mlsanity.com/paper/2003.13964/) (2020)
- [Privacy Risks of Securing Machine Learning Models against Adversarial Examples](https://mlsanity.com/paper/1905.10291/) (2019)
- [Deep Learning Through the Lens of Example Difficulty](https://mlsanity.com/paper/2106.09647/) (2021)
- [The Privacy Onion Effect: Memorization is Relative](https://mlsanity.com/paper/2206.10469/) (2022)
- [On the geometry of generalization and memorization in deep neural networks](https://mlsanity.com/paper/2105.14602/) (2021)
- [Mitigating Membership Inference Attacks by Self-Distillation Through a Novel Ensemble Architecture](https://mlsanity.com/paper/2110.08324/) (2021)
- [Membership Inference Attacks and Defenses in Neural Network Pruning](https://mlsanity.com/paper/2202.03335/) (2022)
- [Pruning has a disparate impact on model accuracy](https://mlsanity.com/paper/2205.13574/) (2022)
- [RelaxLoss: Defending Membership Inference Attacks without Losing Utility](https://mlsanity.com/paper/2207.05801/) (2022)
- [Against Membership Inference Attack: Pruning is All You Need](https://mlsanity.com/paper/2008.13578/) (2020)
- [Overconfidence is a Dangerous Thing: Mitigating Membership Inference Attacks by Enforcing Less Confident Prediction](https://mlsanity.com/paper/2307.01610/) (2023)
- [Privacy Analysis of Deep Learning in the Wild: Membership Inference Attacks against Transfer Learning](https://mlsanity.com/paper/2009.04872/) (2020)
- [Leveraging Adversarial Examples to Quantify Membership Information Leakage](https://mlsanity.com/paper/2203.09566/) (2022)
- [A Blessing of Dimensionality in Membership Inference through Regularization](https://mlsanity.com/paper/2205.14055/) (2022)

## Built on by (most cited first, 1 of 1)

- [Learnability and Privacy Vulnerability are Entangled in a Few Critical Weights](https://mlsanity.com/paper/2603.13186/) (2026)

## Abstract (arXiv)

A deep learning model usually has to sacrifice some utilities when it acquires some other abilities or characteristics. Privacy preservation has such trade-off relationships with utilities. The loss disparity between various defense approaches implies the potential to decouple generalizability and privacy risks to maximize privacy gain. In this paper, we identify that the model's generalization and privacy risks exist in different regions in deep neural network architectures. Based on the observations that we investigate, we propose Privacy-Preserving Training Principle (PPTP) to protect model components from privacy risks while minimizing the loss in generalizability. Through extensive evaluations, our approach shows significantly better maintenance in model generalizability while enhancing privacy preservation.