# A Survey of Privacy Attacks in Machine Learning

arXiv: https://arxiv.org/abs/2007.07646 · HTML: https://mlsanity.com/paper/2007.07646/

## Key facts

- Cited by 146 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Jul 2020.

## Built on by (most cited first, 30 of 146)

- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Large Language Model Alignment: A Survey](https://mlsanity.com/paper/2309.15025/) (2023)
- [FedPara: Low-Rank Hadamard Product for Communication-Efficient Federated Learning](https://mlsanity.com/paper/2108.06098/) (2021)
- [ProPILE: Probing Privacy Leakage in Large Language Models](https://mlsanity.com/paper/2307.01881/) (2023)
- [A Comprehensive Survey on Trustworthy Graph Neural Networks: Privacy, Robustness, Fairness, and Explainability](https://mlsanity.com/paper/2204.08570/) (2022)
- [Trustworthy AI: A Computational Perspective](https://mlsanity.com/paper/2107.06641/) (2021)
- [Ignore This Title and HackAPrompt: Exposing Systemic Vulnerabilities of LLMs through a Global Scale Prompt Hacking Competition](https://mlsanity.com/paper/2311.16119/) (2023)
- [Membership Inference Attacks against Synthetic Data through Overfitting Detection](https://mlsanity.com/paper/2302.12580/) (2023)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [Label-Only Model Inversion Attacks via Boundary Repulsion](https://mlsanity.com/paper/2203.01925/) (2022)
- [SoK: Let the Privacy Games Begin! A Unified Treatment of Data Inference Privacy in Machine Learning](https://mlsanity.com/paper/2212.10986/) (2022)
- [Tricking LLMs into Disobedience: Formalizing, Analyzing, and Detecting Jailbreaks](https://mlsanity.com/paper/2305.14965/) (2023)
- [Operationalizing a Threat Model for Red-Teaming Large Language Models (LLMs)](https://mlsanity.com/paper/2407.14937/) (2024)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [Gradient Obfuscation Gives a False Sense of Security in Federated Learning](https://mlsanity.com/paper/2206.04055/) (2022)
- [Reinforcement Learning-Based Black-Box Model Inversion Attacks](https://mlsanity.com/paper/2304.04625/) (2023)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [On the Privacy Risks of Algorithmic Recourse](https://mlsanity.com/paper/2211.05427/) (2022)
- [FedHM: Efficient Federated Learning for Heterogeneous Models via Low-rank Factorization](https://mlsanity.com/paper/2111.14655/) (2021)
- [Bilateral Dependency Optimization: Defending Against Model-inversion Attacks](https://mlsanity.com/paper/2206.05483/) (2022)
- [Identifying and Mitigating Privacy Risks Stemming from Language Models: A Survey](https://mlsanity.com/paper/2310.01424/) (2023)
- [Beyond Privacy: Navigating the Opportunities and Challenges of Synthetic Data](https://mlsanity.com/paper/2304.03722/) (2023)
- [Model Inversion Attacks against Graph Neural Networks](https://mlsanity.com/paper/2209.07807/) (2022)
- [Sketching for First Order Method: Efficient Algorithm for Low-Bandwidth Channel and Vulnerability](https://mlsanity.com/paper/2210.08371/) (2022)
- [A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications](https://mlsanity.com/paper/2308.16375/) (2023)
- [Gaussian Membership Inference Privacy](https://mlsanity.com/paper/2306.07273/) (2023)
- [The privacy issue of counterfactual explanations: explanation linkage attacks](https://mlsanity.com/paper/2210.12051/) (2022)
- [Property Inference Attacks on Convolutional Neural Networks: Influence and Implications of Target Model's Complexity](https://mlsanity.com/paper/2104.13061/) (2021)
- [Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images](https://mlsanity.com/paper/2404.12922/) (2024)
- [Poison-splat: Computation Cost Attack on 3D Gaussian Splatting](https://mlsanity.com/paper/2410.08190/) (2024)

## Abstract (arXiv)

As machine learning becomes more widely used, the need to study its implications in security and privacy becomes more urgent. Although the body of work in privacy has been steadily growing over the past few years, research on the privacy aspects of machine learning has received less focus than the security aspects. Our contribution in this research is an analysis of more than 40 papers related to privacy attacks against machine learning that have been published during the past seven years. We propose an attack taxonomy, together with a threat model that allows the categorization of different attacks based on the adversarial knowledge, and the assets under attack. An initial exploration of the causes of privacy leaks is presented, as well as a detailed analysis of the different attacks. Finally, we present an overview of the most commonly proposed defenses and a discussion of the open problems and future directions identified during our analysis.