# Unveiling the Unseen: Exploring Whitebox Membership Inference through the Lens of Explainability

arXiv: https://arxiv.org/abs/2407.01306 · HTML: https://mlsanity.com/paper/2407.01306/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Placed in Membership inference attacks, one of 12 directions in LLM safety and security.
- Builds on 13 of its 31 references that are in the map.
- First posted on arXiv 1 Jul 2024.

## Placed in

- LLM safety and security / [Membership inference attacks](https://mlsanity.com/safety/membership-inference-attacks/)

## Builds on (most cited first, 13 of 13)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [How transferable are features in deep neural networks?](https://mlsanity.com/paper/1411.1792/) (2014)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Understanding the Role of Individual Units in a Deep Neural Network](https://mlsanity.com/paper/2009.05041/) (2020)
- [Enhanced Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/2111.09679/) (2021)
- [Understanding Membership Inferences on Well-Generalized Learning Models](https://mlsanity.com/paper/1802.04889/) (2018)
- [ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models](https://mlsanity.com/paper/2102.02551/) (2021)
- [Comprehensive Privacy Analysis of Deep Learning: Passive and Active White-box Inference Attacks against Centralized and Federated Learning](https://mlsanity.com/paper/1812.00910/) (2018)
- [Membership Inference Attacks and Generalization: A Causal Perspective](https://mlsanity.com/paper/2209.08615/) (2022)

## Built on by (most cited first, 6 of 6)

- [SoK: Challenges in Tabular Membership Inference Attacks](https://mlsanity.com/paper/2601.15874/) (2026)
- [AI Security in the Foundation Model Era: A Comprehensive Survey from a Unified Perspective](https://mlsanity.com/paper/2603.24857/) (2026)
- [FRIDA: Free-Rider Detection using Privacy Attacks](https://mlsanity.com/paper/2410.05020/) (2024)
- [SERSEM: Selective Entropy-Weighted Scoring for Membership Inference in Code Language Models](https://mlsanity.com/paper/2604.01147/) (2026)
- [Predicting Privacy Leakage from Weight Spectral Density](https://mlsanity.com/paper/2609.11780/) (2026)
- [SoK: Rethinking Membership Inference in Tabular Machine Learning](https://mlsanity.com/paper/2610.18486/) (2026)

## Abstract (arXiv)

The increasing prominence of deep learning applications and reliance on personalized data underscore the urgent need to address privacy vulnerabilities, particularly Membership Inference Attacks (MIAs). Despite numerous MIA studies, significant knowledge gaps persist, particularly regarding the impact of hidden features (in isolation) on attack efficacy and insufficient justification for the root causes of attacks based on raw data features. In this paper, we aim to address these knowledge gaps by first exploring statistical approaches to identify the most informative neurons and quantifying the significance of the hidden activations from the selected neurons on attack accuracy, in isolation and combination. Additionally, we propose an attack-driven explainable framework by integrating the target and attack models to identify the most influential features of raw data that lead to successful membership inference attacks. Our proposed MIA shows an improvement of up to 26% on state-of-the-art MIA.