CRLGJun 30, 2021

Bio-Inspired Adversarial Attack Against Deep Neural Networks

arXiv:2107.02895v11 citations
Originality Highly original
AI Analysis

This addresses security vulnerabilities in AI systems for applications like autonomous vehicles and surveillance, presenting a novel physical attack approach.

The paper tackles the problem of adversarial attacks on deep neural networks by introducing bio-inspired moving physical objects, demonstrating that superimposing patterns on flapping wing robots can cause targeted misclassification and that specific motions can make object detectors blind in videos.

The paper develops a new adversarial attack against deep neural networks (DNN), based on applying bio-inspired design to moving physical objects. To the best of our knowledge, this is the first work to introduce physical attacks with a moving object. Instead of following the dominating attack strategy in the existing literature, i.e., to introduce minor perturbations to a digital input or a stationary physical object, we show two new successful attack strategies in this paper. We show by superimposing several patterns onto one physical object, a DNN becomes confused and picks one of the patterns to assign a class label. Our experiment with three flapping wing robots demonstrates the possibility of developing an adversarial camouflage to cause a targeted mistake by DNN. We also show certain motion can reduce the dependency among consecutive frames in a video and make an object detector "blind", i.e., not able to detect an object exists in the video. Hence in a successful physical attack against DNN, targeted motion against the system should also be considered.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes