Developing and Defeating Adversarial Examples

TL;DR

This paper explores the creation of adversarial examples to attack the Yolo V3 object detector and investigates methods to detect and neutralize these attacks, highlighting safety concerns in deploying DNNs.

Contribution

It develops adversarial examples against Yolo V3 and proposes strategies for their detection and neutralization, advancing robustness in object detection models.

Findings

Successfully generated adversarial examples for Yolo V3

Proposed detection methods for adversarial inputs

Demonstrated neutralization techniques for adversarial attacks

Abstract

Breakthroughs in machine learning have resulted in state-of-the-art deep neural networks (DNNs) performing classification tasks in safety-critical applications. Recent research has demonstrated that DNNs can be attacked through adversarial examples, which are small perturbations to input data that cause the DNN to misclassify objects. The proliferation of DNNs raises important safety concerns about designing systems that are robust to adversarial examples. In this work we develop adversarial examples to attack the Yolo V3 object detector [1] and then study strategies to detect and neutralize these examples. Python code for this project is available at https://github.com/ianmcdiarmidsterling/adversarial