دورية أكاديمية
Adversarial-Aware Deep Learning System Based on a Secondary Classical Machine Learning Verification Approach.
| العنوان: | Adversarial-Aware Deep Learning System Based on a Secondary Classical Machine Learning Verification Approach. |
|---|---|
| المؤلفون: | Alkhowaiter M; College of Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA.; College of Computer Engineering and Science, Prince Sattam Bin Abdulaziz University, Al-Kharj 11942, Saudi Arabia., Kholidy H; College of Engineering, SUNY Polytechnic Institute, Utica, NY 13502, USA., Alyami MA; College of Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA., Alghamdi A; College of Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA., Zou C; College of Engineering and Computer Science, University of Central Florida, Orlando, FL 32816, USA. |
| المصدر: | Sensors (Basel, Switzerland) [Sensors (Basel)] 2023 Jul 11; Vol. 23 (14). Date of Electronic Publication: 2023 Jul 11. |
| نوع المنشور: | Journal Article |
| اللغة: | English |
| بيانات الدورية: | Publisher: MDPI Country of Publication: Switzerland NLM ID: 101204366 Publication Model: Electronic Cited Medium: Internet ISSN: 1424-8220 (Electronic) Linking ISSN: 14248220 NLM ISO Abbreviation: Sensors (Basel) Subsets: PubMed not MEDLINE; MEDLINE |
| أسماء مطبوعة: | Original Publication: Basel, Switzerland : MDPI, c2000- |
| مستخلص: | Deep learning models have been used in creating various effective image classification applications. However, they are vulnerable to adversarial attacks that seek to misguide the models into predicting incorrect classes. Our study of major adversarial attack models shows that they all specifically target and exploit the neural networking structures in their designs. This understanding led us to develop a hypothesis that most classical machine learning models, such as random forest (RF), are immune to adversarial attack models because they do not rely on neural network design at all. Our experimental study of classical machine learning models against popular adversarial attacks supports this hypothesis. Based on this hypothesis, we propose a new adversarial-aware deep learning system by using a classical machine learning model as the secondary verification system to complement the primary deep learning model in image classification. Although the secondary classical machine learning model has less accurate output, it is only used for verification purposes, which does not impact the output accuracy of the primary deep learning model, and, at the same time, can effectively detect an adversarial attack when a clear mismatch occurs. Our experiments based on the CIFAR-100 dataset show that our proposed approach outperforms current state-of-the-art adversarial defense systems. |
| References: | Ecology. 2007 Nov;88(11):2783-92. (PMID: 18051647) Psychol Methods. 2009 Dec;14(4):323-48. (PMID: 19968396) |
| فهرسة مساهمة: | Keywords: adversarial machine learning; computer security; deep neural networks; image forensics; image manipulation detection |
| تواريخ الأحداث: | Date Created: 20230729 Latest Revision: 20230731 |
| رمز التحديث: | 20231215 |
| مُعرف محوري في PubMed: | PMC10384939 |
| DOI: | 10.3390/s23146287 |
| PMID: | 37514582 |
| قاعدة البيانات: | MEDLINE |
Full Text Finder كن أول من يترك تعليقا!