The Attack Generator: A Systematic Approach Towards Constructing Adversarial Attacks
This work addresses the challenge of adversarial robustness for safety-critical ML deployments, such as autonomous driving, by providing a structured approach to attack generation, though it appears incremental as it builds on existing taxonomies.
The paper tackles the unstructured nature of adversarial attack research by proposing a systematic 'attack generator' framework that analyzes and categorizes building blocks of attacks, applying it to computer vision systems for autonomous vehicles like semantic segmentation and object detection.
Most state-of-the-art machine learning (ML) classification systems are vulnerable to adversarial perturbations. As a consequence, adversarial robustness poses a significant challenge for the deployment of ML-based systems in safety- and security-critical environments like autonomous driving, disease detection or unmanned aerial vehicles. In the past years we have seen an impressive amount of publications presenting more and more new adversarial attacks. However, the attack research seems to be rather unstructured and new attacks often appear to be random selections from the unlimited set of possible adversarial attacks. With this publication, we present a structured analysis of the adversarial attack creation process. By detecting different building blocks of adversarial attacks, we outline the road to new sets of adversarial attacks. We call this the "attack generator". In the pursuit of this objective, we summarize and extend existing adversarial perturbation taxonomies. The resulting taxonomy is then linked to the application context of computer vision systems for autonomous vehicles, i.e. semantic segmentation and object detection. Finally, in order to prove the usefulness of the attack generator, we investigate existing semantic segmentation attacks with respect to the detected defining components of adversarial attacks.