DeepAI AI Chat
Log In Sign Up

Feature Distillation With Guided Adversarial Contrastive Learning

by   Tao Bai, et al.

Deep learning models are shown to be vulnerable to adversarial examples. Though adversarial training can enhance model robustness, typical approaches are computationally expensive. Recent works proposed to transfer the robustness to adversarial attacks across different tasks or models with soft labels.Compared to soft labels, feature contains rich semantic information and holds the potential to be applied to different downstream tasks. In this paper, we propose a novel approach called Guided Adversarial Contrastive Distillation (GACD), to effectively transfer adversarial robustness from teacher to student with features. We first formulate this objective as contrastive learning and connect it with mutual information. With a well-trained teacher model as an anchor, students are expected to extract features similar to the teacher. Then considering the potential errors made by teachers, we propose sample reweighted estimation to eliminate the negative effects from teachers. With GACD, the student not only learns to extract robust features, but also captures structural knowledge from the teacher. By extensive experiments evaluating over popular datasets such as CIFAR-10, CIFAR-100 and STL-10, we demonstrate that our approach can effectively transfer robustness across different models and even different tasks, and achieve comparable or better results than existing methods. Besides, we provide a detailed analysis of various methods, showing that students produced by our approach capture more structural knowledge from teachers and learn more robust features under adversarial attacks.


page 1

page 2

page 3

page 4


Revisiting Adversarial Robustness Distillation: Robust Soft Labels Make Student Better

Adversarial training is one effective approach for training robust deep ...

Mutual Adversarial Training: Learning together is better than going alone

Recent studies have shown that robustness to adversarial attacks can be ...

Complementary Relation Contrastive Distillation

Knowledge distillation aims to transfer representation ability from a te...

Accelerating Certified Robustness Training via Knowledge Transfer

Training deep neural network classifiers that are certifiably robust aga...

Reliable Adversarial Distillation with Unreliable Teachers

In ordinary distillation, student networks are trained with soft labels ...

Understanding Robustness in Teacher-Student Setting: A New Perspective

Adversarial examples have appeared as a ubiquitous property of machine l...

Contrastive Knowledge Amalgamation for Unsupervised Image Classification

Knowledge amalgamation (KA) aims to learn a compact student model to han...