On the Effectiveness of Defensive Distillation

2016/07/18 by Nicolas Papernot, Patrick McDaniel, Papernot, Nicolas +1
Computer Science · Engineering · #Adversarial Robustness in Machine Learning #Computational Drug Discovery Methods #Cryptography and Security (cs.CR) #FOS: Computer and information sciences #Fault Detection and Control Systems

paper · pdf · doi:10.48550/arxiv.1607.05113

openalex publication_date 2016/07/18 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

We report experimental results indicating that defensive distillation successfully mitigates adversarial samples crafted using the fast gradient sign method, in addition to those crafted using the Jacobian-based iterative attack on which the defense mechanism was originally evaluated.

Citations

• Gradient-based learning applied to document recognition
• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples

Related

• Defensive Distillation is Not Robust to Adversarial Examples
• Extending Defensive Distillation
• Distillation as a Defense to Adversarial Perturbations against Deep\n Neural Networks
• Why Blocking Targeted Adversarial Perturbations Impairs the Ability to Learn
• Improving Defensive Distillation using Teacher Assistant