Adversarial Attack for Asynchronous Event-based Data

TL;DR

This paper introduces a novel adversarial attack method for event-based data, shifting event timings and adding adversarial events to fool DNNs, and demonstrates improved robustness through adversarial training.

Contribution

It is the first to generate adversarial examples for event-based data and proposes a two-stage method involving null events and gradient-based attacks.

Findings

Achieves 97.95% attack success rate on N-Caltech101 dataset.

Adversarial training enhances model robustness against adversarial event data.

Introduces a new approach for adversarial attacks specific to event-based data.

Abstract

Deep neural networks (DNNs) are vulnerable to adversarial examples that are carefully designed to cause the deep learning model to make mistakes. Adversarial examples of 2D images and 3D point clouds have been extensively studied, but studies on event-based data are limited. Event-based data can be an alternative to a 2D image under high-speed movements, such as autonomous driving. However, the given adversarial events make the current deep learning model vulnerable to safety issues. In this work, we generate adversarial examples and then train the robust models for event-based data, for the first time. Our algorithm shifts the time of the original events and generates additional adversarial events. Additional adversarial events are generated in two stages. First, null events are added to the event-based data to generate additional adversarial events. The perturbation size can be controlled with the number of null events. Second, the location and time of additional adversarial events are set to mislead DNNs in a gradient-based attack. Our algorithm achieves an attack success rate of 97.95\% on the N-Caltech101 dataset. Furthermore, the adversarial training model improves robustness on the adversarial event data compared to the original model.