Privacy & Differential Privacy in Machine Learning Reading List

Curated by Mouhssine Rifaki | Stanford Electrical Engineering | Last updated August 2026

Privacy must be built in, not bolted on. This list covers differential privacy foundations, DP-SGD, and private aggregation.

Privacy & Differential Privacy in Machine Learning: 10 key papers

1. Deep Learning with Differential Privacy
   Abadi et al. arXiv 2016.
2. The Algorithmic Foundations of Differential Privacy
   Dwork and Roth. 2013.
3. Membership Inference Attacks against Machine Learning Models
   Shokri et al. arXiv 2016.
4. Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data
   Papernot et al. arXiv 2016.
5. Extracting Training Data from Large Language Models
   Carlini et al. arXiv 2020.
6. Deep Leakage from Gradients
   Zhu et al. arXiv 2019.
7. Differentially Private Empirical Risk Minimization
   Chaudhuri et al. arXiv 2009.
8. Renyi Differential Privacy
   Mironov. arXiv 2017.
9. Evaluating Differentially Private Machine Learning in Practice
   Jayaraman and Evans. arXiv 2019.
10. Tempered Sigmoid Activations for Deep Learning with Differential Privacy
    Papernot et al. arXiv 2020.

Related reading lists

• Certified Robustness
• Physics-Informed Machine Learning & Scientific ML
• Score-Based Generative Modeling
• Neural ODEs & Continuous-Time Models
• Knowledge Distillation
• Neural Operators & PDE Solvers
• Fairness & Bias in ML
• Self-Play & Population-Based Training