On the Effectiveness of Defensive Distillation

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.

arXiv commentTechnical Report

References in corpus (1)

• Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samples

Cited by in corpus (17)

• Towards Deep Learning Models Resistant to Adversarial Attacks
• Stochastic Activation Pruning for Robust Adversarial Defense
• Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey
• DeepSafe: A Data-driven Approach for Checking Adversarial Robustness in Neural Networks
• Learning Adversary-Resistant Deep Neural Networks
• PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
• Improving adversarial robustness of deep neural networks by using semantic information
• Certifiably Robust Interpretation in Deep Learning
• Adversarial Robustness via Label-Smoothing
• Towards Security Threats of Deep Learning Systems: A Survey
• Subset Scanning Over Neural Network Activations
• DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning
• Query-Free Attacks on Industry-Grade Face Recognition Systems under Resource Constraints
• Unifying Bilateral Filtering and Adversarial Training for Robust Neural Networks
• The Human Visual System and Adversarial AI
• Ensemble Generative Cleaning with Feedback Loops for Defending Adversarial Attacks
• Adversarial Ranking Attack and Defense