# Privacy in Deep Learning: A Survey

arXiv: https://arxiv.org/abs/2004.12254 · HTML: https://mlsanity.com/paper/2004.12254/

## Key facts

- Cited by 71 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Apr 2020.

## Built on by (most cited first, 30 of 71)

- [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)
- [Quantifying Privacy Risks of Masked Language Models Using Membership Inference Attacks](https://mlsanity.com/paper/2203.03929/) (2022)
- [Federated Learning for Open Banking](https://mlsanity.com/paper/2108.10749/) (2021)
- [Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Survey](https://mlsanity.com/paper/2210.07700/) (2022)
- [Towards Modular LLMs by Building and Reusing a Library of LoRAs](https://mlsanity.com/paper/2405.11157/) (2024)
- [Clio: Privacy-Preserving Insights into Real-World AI Use](https://mlsanity.com/paper/2412.13678/) (2024)
- [Large Language Model Safety: A Holistic Survey](https://mlsanity.com/paper/2412.17686/) (2024)
- [Socially Responsible AI Algorithms: Issues, Purposes, and Challenges](https://mlsanity.com/paper/2101.02032/) (2021)
- [MultiTrust: A Comprehensive Benchmark Towards Trustworthy Multimodal Large Language Models](https://mlsanity.com/paper/2406.07057/) (2024)
- [FedMultimodal: A Benchmark For Multimodal Federated Learning](https://mlsanity.com/paper/2306.09486/) (2023)
- [Memorization in NLP Fine-tuning Methods](https://mlsanity.com/paper/2205.12506/) (2022)
- [Membership Inference on Word Embedding and Beyond](https://mlsanity.com/paper/2106.11384/) (2021)
- [DP-SGD vs PATE: Which Has Less Disparate Impact on Model Accuracy?](https://mlsanity.com/paper/2106.12576/) (2021)
- [A Comprehensive Survey on Trustworthy Recommender Systems](https://mlsanity.com/paper/2209.10117/) (2022)
- [Privacy Regularization: Joint Privacy-Utility Optimization in Language Models](https://mlsanity.com/paper/2103.07567/) (2021)
- [UserIdentifier: Implicit User Representations for Simple and Effective Personalized Sentiment Analysis](https://mlsanity.com/paper/2110.00135/) (2021)
- [A Survey on Privacy in Graph Neural Networks: Attacks, Preservation, and Applications](https://mlsanity.com/paper/2308.16375/) (2023)
- [Collaborative Intelligence: Challenges and Opportunities](https://mlsanity.com/paper/2102.06841/) (2021)
- [Honest-but-Curious Nets: Sensitive Attributes of Private Inputs Can Be Secretly Coded into the Classifiers' Outputs](https://mlsanity.com/paper/2105.12049/) (2021)
- [Reasoning Capacity in Multi-Agent Systems: Limitations, Challenges and Human-Centered Solutions](https://mlsanity.com/paper/2402.01108/) (2024)
- [DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware](https://mlsanity.com/paper/2207.00083/) (2022)
- [Differentially Private Model Compression](https://mlsanity.com/paper/2206.01838/) (2022)
- [A Review of Speech-centric Trustworthy Machine Learning: Privacy, Safety, and Fairness](https://mlsanity.com/paper/2212.09006/) (2022)
- [Attribute Inference Attack of Speech Emotion Recognition in Federated Learning Settings](https://mlsanity.com/paper/2112.13416/) (2021)
- [Recent Advances of Differential Privacy in Centralized Deep Learning: A Systematic Survey](https://mlsanity.com/paper/2309.16398/) (2023)
- [Binarizing Split Learning for Data Privacy Enhancement and Computation Reduction](https://mlsanity.com/paper/2206.04864/) (2022)
- [Unsupervised Deep Learning for IoT Time Series](https://mlsanity.com/paper/2302.03284/) (2023)
- [Interference Suppression Using Deep Learning: Current Approaches and Open Challenges](https://mlsanity.com/paper/2112.08988/) (2021)
- [Privacy Leakage in Text Classification: A Data Extraction Approach](https://mlsanity.com/paper/2206.04591/) (2022)

## Abstract (arXiv)

The ever-growing advances of deep learning in many areas including vision, recommendation systems, natural language processing, etc., have led to the adoption of Deep Neural Networks (DNNs) in production systems. The availability of large datasets and high computational power are the main contributors to these advances. The datasets are usually crowdsourced and may contain sensitive information. This poses serious privacy concerns as this data can be misused or leaked through various vulnerabilities. Even if the cloud provider and the communication link is trusted, there are still threats of inference attacks where an attacker could speculate properties of the data used for training, or find the underlying model architecture and parameters. In this survey, we review the privacy concerns brought by deep learning, and the mitigating techniques introduced to tackle these issues. We also show that there is a gap in the literature regarding test-time inference privacy, and propose possible future research directions.