Certified Robustness Reading List

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

Foundational papers on certified robustness, including randomized smoothing, interval bounds, and provable verification.

Certified Robustness: 10 key papers

1. Certified Adversarial Robustness via Randomized Smoothing
   Cohen et al. arXiv 2019.
2. Towards Deep Learning Models Resistant to Adversarial Attacks
   Madry et al. arXiv 2017.
3. Certified Defenses against Adversarial Examples
   Raghunathan et al. arXiv 2018.
4. Provable defenses against adversarial examples via the convex outer adversarial polytope
   Wong and Kolter. arXiv 2017.
5. Efficient Neural Network Robustness Certification with General Activation Functions
   Zhang et al. arXiv 2018.
6. Evaluating Robustness of Neural Networks with Mixed Integer Programming
   Tjeng et al. arXiv 2017.
7. On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models
   Gowal et al. arXiv 2018.
8. Certified Robustness to Adversarial Examples with Differential Privacy
   Lecuyer et al. arXiv 2018.
9. Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks
   Katz et al. arXiv 2017.
10. Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verification
    Wang et al. arXiv 2021.

Related reading lists

• Adversarial Reinforcement Learning & Robustness to Adversaries
• Privacy & Differential Privacy in Machine Learning
• Out-of-Distribution & Robustness
• Sample Complexity in Reinforcement Learning
• Quantization for Efficient Inference
• Robust & Risk-Sensitive RL
• Optimal Control & LQR/LQG
• Imitation Learning and Inverse RL