CAAD 2018: Iterative Ensemble Adversarial Attack
This work addresses the vulnerability of deep neural networks to adversarial examples, which is crucial for evaluating model robustness before deployment, though it is incremental as it builds on existing attack methods.
The paper tackled the problem of low success rates in black-box adversarial attacks by proposing an iterative adversarial attack against an ensemble of image classifiers, achieving 5th place in the CAAD 2018 Targeted Adversarial Attack competition.
Deep Neural Networks (DNNs) have recently led to significant improvements in many fields. However, DNNs are vulnerable to adversarial examples which are samples with imperceptible perturbations while dramatically misleading the DNNs. Adversarial attacks can be used to evaluate the robustness of deep learning models before they are deployed. Unfortunately, most of existing adversarial attacks can only fool a black-box model with a low success rate. To improve the success rates for black-box adversarial attacks, we proposed an iterated adversarial attack against an ensemble of image classifiers. With this method, we won the 5th place in CAAD 2018 Targeted Adversarial Attack competition.