SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODEL
Artificial intelligence (AI) has found applications across various sectors and industries, offering numerous advantages to human beings. One prominent area where AI has made significant contributions is in machine learning models. These models have revolutionized various fields, benefiting society i...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Dalat University
2024-08-01
|
| Series: | Tạp chí Khoa học Đại học Đà Lạt |
| Subjects: | |
| Online Access: | https://tckh.dlu.edu.vn/index.php/tckhdhdl/article/view/1150 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1823857066638311424 |
|---|---|
| author | Thanh Son Phan Quang Hua Ta Duy Trung Pham Phi Ho Truong |
| author_facet | Thanh Son Phan Quang Hua Ta Duy Trung Pham Phi Ho Truong |
| author_sort | Thanh Son Phan |
| collection | DOAJ |
| description | Artificial intelligence (AI) has found applications across various sectors and industries, offering numerous advantages to human beings. One prominent area where AI has made significant contributions is in machine learning models. These models have revolutionized various fields, benefiting society in numerous ways, from self-driving cars and intelligent chatbots to automated facial authentication systems. However, in recent years, machine learning models have been the target of various attack methods. One common and dangerous attack method is adversarial attack, where modified input images can cause misclassification or erroneous predictions by the models. To confront that challenge, we present a novel approach called adversarial retraining that uses adversarial examples to train machine learning and deep learning models. This technique aims to enhance the robustness and performance of these models by subjecting them to adversarial scenarios during the training process. In this paper, we survey detection methods and propose a method to detect adversarial examples using YOLOv7, a commonly used intensive research model. By training adversarial retraining and conducting experiments, we show that the proposed method is an effective solution for helping deep learning models detect certain cases of adversarial examples.
|
| format | Article |
| id | doaj-art-7698f8dc161b4756906789cab4887f6f |
| institution | Kabale University |
| issn | 0866-787X |
| language | English |
| publishDate | 2024-08-01 |
| publisher | Dalat University |
| record_format | Article |
| series | Tạp chí Khoa học Đại học Đà Lạt |
| spelling | doaj-art-7698f8dc161b4756906789cab4887f6f2025-02-12T01:00:49ZengDalat UniversityTạp chí Khoa học Đại học Đà Lạt0866-787X2024-08-0114310.37569/DalatUniversity.14.3.1150(2024)SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODELThanh Son Phan0https://orcid.org/0009-0000-6110-2586Quang Hua Ta1https://orcid.org/0009-0008-8244-1446Duy Trung Pham2https://orcid.org/0009-0009-0986-7093Phi Ho Truong3https://orcid.org/0009-0004-9119-4353Telecommunications UniversityAcademy of Cryptography TechniquesAcademy of Cryptography TechniquesAcademy of Cryptography TechniquesArtificial intelligence (AI) has found applications across various sectors and industries, offering numerous advantages to human beings. One prominent area where AI has made significant contributions is in machine learning models. These models have revolutionized various fields, benefiting society in numerous ways, from self-driving cars and intelligent chatbots to automated facial authentication systems. However, in recent years, machine learning models have been the target of various attack methods. One common and dangerous attack method is adversarial attack, where modified input images can cause misclassification or erroneous predictions by the models. To confront that challenge, we present a novel approach called adversarial retraining that uses adversarial examples to train machine learning and deep learning models. This technique aims to enhance the robustness and performance of these models by subjecting them to adversarial scenarios during the training process. In this paper, we survey detection methods and propose a method to detect adversarial examples using YOLOv7, a commonly used intensive research model. By training adversarial retraining and conducting experiments, we show that the proposed method is an effective solution for helping deep learning models detect certain cases of adversarial examples. https://tckh.dlu.edu.vn/index.php/tckhdhdl/article/view/1150Adversarial examplesDeep learningObject detectionTrained model. |
| spellingShingle | Thanh Son Phan Quang Hua Ta Duy Trung Pham Phi Ho Truong SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODEL Tạp chí Khoa học Đại học Đà Lạt Adversarial examples Deep learning Object detection Trained model. |
| title | SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODEL |
| title_full | SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODEL |
| title_fullStr | SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODEL |
| title_full_unstemmed | SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODEL |
| title_short | SURVEY AND PROPOSED METHOD TO DETECT ADVERSARIAL EXAMPLES USING AN ADVERSARIAL RETRAINING MODEL |
| title_sort | survey and proposed method to detect adversarial examples using an adversarial retraining model |
| topic | Adversarial examples Deep learning Object detection Trained model. |
| url | https://tckh.dlu.edu.vn/index.php/tckhdhdl/article/view/1150 |
| work_keys_str_mv | AT thanhsonphan surveyandproposedmethodtodetectadversarialexamplesusinganadversarialretrainingmodel AT quanghuata surveyandproposedmethodtodetectadversarialexamplesusinganadversarialretrainingmodel AT duytrungpham surveyandproposedmethodtodetectadversarialexamplesusinganadversarialretrainingmodel AT phihotruong surveyandproposedmethodtodetectadversarialexamplesusinganadversarialretrainingmodel |