Robust-Compression.md

Defense

Pruning

• Sparse DNNs with improved adversarial robustness
• Adversarial Robustness vs. Model Compression, or Both?
• Adversarial Robustness Of Pruned Neural Networks
• Stochastic activation pruning for robust adversarial defense
• DeepCloak: Masking deep neural network models for robustness against adversarial samples (ICLR2017-Workshop)

Quantization

• Defensive Quantization: When Efficiency Meets Robustness
• EMPIR: Ensembles of Mixed Precision Deep Networks for Increased Robustness Against Adversarial Attacks

Distillation

• Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks

Attack

• Combinatorial attacks on binarized neural networks
• Attacking binarized neural networks