Enhancing Accuracy and Robustness through Adversarial Training in Class Incremental Continual Learning

by   Minchan Kwon, et al.

In real life, adversarial attack to deep learning models is a fatal security issue. However, the issue has been rarely discussed in a widely used class-incremental continual learning (CICL). In this paper, we address problems of applying adversarial training to CICL, which is well-known defense method against adversarial attack. A well-known problem of CICL is class-imbalance that biases a model to the current task by a few samples of previous tasks. Meeting with the adversarial training, the imbalance causes another imbalance of attack trials over tasks. Lacking clean data of a minority class by the class-imbalance and increasing of attack trials from a majority class by the secondary imbalance, adversarial training distorts optimal decision boundaries. The distortion eventually decreases both accuracy and robustness than adversarial training. To exclude the effects, we propose a straightforward but significantly effective method, External Adversarial Training (EAT) which can be applied to methods using experience replay. This method conduct adversarial training to an auxiliary external model for the current task data at each time step, and applies generated adversarial examples to train the target model. We verify the effects on a toy problem and show significance on CICL benchmarks of image classification. We expect that the results will be used as the first baseline for robustness research of CICL.


page 3

page 4


Recent Advances in Adversarial Training for Adversarial Robustness

Adversarial training is one of the most effective approaches defending a...

Training Time Adversarial Attack Aiming the Vulnerability of Continual Learning

Generally, regularization-based continual learning models limit access t...

Analysis and Applications of Class-wise Robustness in Adversarial Training

Adversarial training is one of the most effective approaches to improve ...

PIAT: Parameter Interpolation based Adversarial Training for Image Classification

Adversarial training has been demonstrated to be the most effective appr...

Omnipotent Adversarial Training for Unknown Label-noisy and Imbalanced Datasets

Adversarial training is an important topic in robust deep learning, but ...

Understanding the Interaction of Adversarial Training with Noisy Labels

Noisy labels (NL) and adversarial examples both undermine trained models...

Predicting Query-Item Relationship using Adversarial Training and Robust Modeling Techniques

We present an effective way to predict search query-item relationship. W...

Please sign up or login with your details

Forgot password? Click here to reset