Tailoring Adversarial Attacks on Deep Neural Networks for Targeted Class Manipulation Using DeepFool Algorithm
Preprint
Abstract
Deep neural networks (DNNs) have significantly advanced various domains, but their vulnerability to adversarial attacks poses serious concerns. Understanding these vulnerabilities and developing effective defense mechanisms is crucial. DeepFool, an algorithm proposed by Moosavi-Dezfooli et al. (2016), finds minimal perturbations to misclassify input images. However, DeepFool lacks a targeted approach, making it less effective in specific attack scenarios. Also, in previous related works, researchers primarily focus on success, not considering how much an image is getting distorted; the integrity of the image quality, and the confidence level to misclassifying. So, in this paper, we propose Targeted DeepFool, an augmented version of DeepFool that allows targeting specific classes for misclassification. We also introduce a minimum confidence score requirement hyperparameter to enhance flexibility. Our experiments demonstrate the effectiveness and efficiency of the proposed method across different deep neural network architectures while preserving image integrity as much as possible. Results show that one of the deep convolutional neural network architectures, AlexNet, and one of the state-of-the-art model Vision Transformer exhibit high robustness to getting fooled. Our code will be made public when publishing the paper.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Deep learning in computer vision: A critical review of emerging techniques and application scenariosMachine Learning with Applications, 2021
- Patch-Wise Attack for Fooling Deep Neural Network2020
- Towards Transferable Targeted Attack2020
- Mastering the game of Go without human knowledgeNature, 2017
- Towards Evaluating the Robustness of Neural Networks2017
- DeepFool: A Simple and Accurate Method to Fool Deep Neural Networks2016
- Rethinking the Inception Architecture for Computer Vision2016
- The Limitations of Deep Learning in Adversarial Settings2016
- Going deeper with convolutions2015
- Deep Neural Networks for Acoustic Modeling in Speech Recognition: The Shared Views of Four Research GroupsIEEE Signal Processing Magazine, 2012