# ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models

arXiv: https://arxiv.org/abs/1806.01246 · HTML: https://mlsanity.com/paper/1806.01246/

## Key facts

- Cited by 498 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 4 Jun 2018.

## Built on by (most cited first, 30 of 498)

- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Enhanced Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/2111.09679/) (2021)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [Dataset Distillation using Neural Feature Regression](https://mlsanity.com/paper/2206.00719/) (2022)
- [Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks](https://mlsanity.com/paper/2203.03929/) (2022)
- [Reconstructing Training Data with Informed Adversaries](https://mlsanity.com/paper/2201.04845/) (2022)
- [On the Importance of Difficulty Calibration in Membership Inference Attacks](https://mlsanity.com/paper/2111.08440/) (2021)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Are Diffusion Models Vulnerable to Membership Inference Attacks?](https://mlsanity.com/paper/2302.01316/) (2023)
- [Zero-Shot Machine Unlearning](https://mlsanity.com/paper/2201.05629/) (2022)
- [Reconstructing Training Data from Trained Neural Networks](https://mlsanity.com/paper/2206.07758/) (2022)
- [A Comprehensive Survey of Dataset Distillation](https://mlsanity.com/paper/2301.05603/) (2023)
- [Decentralized Federated Averaging](https://mlsanity.com/paper/2104.11375/) (2021)
- [Low-Cost High-Power Membership Inference Attacks](https://mlsanity.com/paper/2312.03262/) (2023)
- [Membership Inference Attacks by Exploiting Loss Trajectory](https://mlsanity.com/paper/2208.14933/) (2022)
- [KGA: A General Machine Unlearning Framework Based on Knowledge Gap Alignment](https://mlsanity.com/paper/2305.06535/) (2023)
- [Practical Membership Inference Attacks against Fine-tuned Large Language Models via Self-prompt Calibration](https://mlsanity.com/paper/2311.06062/) (2023)
- [Does BERT Pretrained on Clinical Notes Reveal Sensitive Data?](https://mlsanity.com/paper/2104.07762/) (2021)
- [BppAttack: Stealthy and Efficient Trojan Attacks against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning](https://mlsanity.com/paper/2205.13383/) (2022)
- [Membership Inference Attacks against Diffusion Models](https://mlsanity.com/paper/2302.03262/) (2023)
- [ML-Doctor: Holistic Risk Assessment of Inference Attacks Against Machine Learning Models](https://mlsanity.com/paper/2102.02551/) (2021)
- [Node-Level Membership Inference Attacks Against Graph Neural Networks](https://mlsanity.com/paper/2102.05429/) (2021)
- [Membership Inference Attack on Graph Neural Networks](https://mlsanity.com/paper/2101.06570/) (2021)
- [Practical Blind Membership Inference Attack via Differential Comparisons](https://mlsanity.com/paper/2101.01341/) (2021)
- [EncoderMI: Membership Inference against Pre-trained Encoders in Contrastive Learning](https://mlsanity.com/paper/2108.11023/) (2021)
- [Federated Unlearning with Knowledge Distillation](https://mlsanity.com/paper/2201.09441/) (2022)

## Abstract (arXiv)

Machine learning (ML) has become a core component of many real-world applications and training data is a key factor that drives current progress. This huge success has led Internet companies to deploy machine learning as a service (MLaaS). Recently, the first membership inference attack has shown that extraction of information on the training set is possible in such MLaaS settings, which has severe security and privacy implications. However, the early demonstrations of the feasibility of such attacks have many assumptions on the adversary, such as using multiple so-called shadow models, knowledge of the target model structure, and having a dataset from the same distribution as the target model's training data. We relax all these key assumptions, thereby showing that such attacks are very broadly applicable at low cost and thereby pose a more severe risk than previously thought. We present the most comprehensive study so far on this emerging and developing threat using eight diverse datasets which show the viability of the proposed attacks across domains. In addition, we propose the first effective defense mechanisms against such broader class of membership inference attacks that maintain a high level of utility of the ML model.