Curriculum Adversarial Training

Abstract

Recently, deep learning has been applied to many security-sensitive applications, such as facial authentication. The existence of adversarial examples hinders such applications. The state-of-the-art result on defense shows that adversarial training can be applied to train a robust model on MNIST against adversarial examples; but it fails to achieve a high empirical worst-case accuracy on a more complex task, such as CIFAR-10 and SVHN. In our work, we propose curriculum adversarial training (CAT) to resolve this issue. The basic idea is to develop a curriculum of adversarial examples generated by attacks with a wide range of strengths. With two techniques to mitigate the forgetting and the generalization issues, we demonstrate that CAT can improve the prior art's empirical worst-case accuracy by a large margin of 25% on CIFAR-10 and 35% on SVHN. At the same, the model's performance on non-adversarial inputs is comparable to the state-of-the-art models.

IJCAI 2018

References in corpus (5)

• Delving into Transferable Adversarial Examples and Black-box Attacks
• Provable defenses against adversarial examples via the convex outer adversarial polytope
• Adversarial Machine Learning at Scale
• DeepDriving: Learning Affordance for Direct Perception in Autonomous Driving
• Attacking the Madry Defense Model with $L_1$-based Adversarial Examples

Cited by in corpus (24)

• Attacks Which Do Not Kill Training Make Adversarial Learning Stronger
• Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Information
• Recent Advances in Adversarial Training for Adversarial Robustness
• Confidence-Calibrated Adversarial Training: Generalizing to Unseen Attacks
• Geometry-aware Instance-reweighted Adversarial Training
• Understanding the Interaction of Adversarial Training with Noisy Labels
• Bag of Tricks for Adversarial Training
• CIFS: Improving Adversarial Robustness of CNNs via Channel-wise Importance-based Feature Selection
• Distributionally Adversarial Attack
• Efficient Adversarial Training with Transferable Adversarial Examples
• Neural Architecture Dilation for Adversarial Robustness
• PointCloud Saliency Maps
• An Optimal Control View of Adversarial Machine Learning
• Detecting Adversarial Examples from Sensitivity Inconsistency of Spatial-Transform Domain
• Guided Interpolation for Adversarial Training
• Detecting Localized Adversarial Examples: A Generic Approach using Critical Region Analysis
• Learning Diverse-Structured Networks for Adversarial Robustness
• Push Stricter to Decide Better: A Class-Conditional Feature Adaptive Framework for Improving Adversarial Robustness
• Dynamic Efficient Adversarial Training Guided by Gradient Magnitude
• Domain Invariant Adversarial Learning
• Enabling Cyberattack-Resilient Load Forecasting through Adversarial Machine Learning
• MGA: Momentum Gradient Attack on Network
• Get Fooled for the Right Reason: Improving Adversarial Robustness through a Teacher-guided Curriculum Learning Approach
• Robust Face Verification via Disentangled Representations