Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification
The Internet of Things environment (e.g., smart phones, smart televisions, and smart watches) ensures that the end user experience is easy, by connecting lives on web services via the internet. Integrating Internet of Things devices poses ethical risks related to data security, privacy, reliability...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/10/15/1798 |
| _version_ | 1797525719687888896 |
|---|---|
| author | Stephen Dankwa Lu Yang |
| author_facet | Stephen Dankwa Lu Yang |
| author_sort | Stephen Dankwa |
| collection | DOAJ |
| description | The Internet of Things environment (e.g., smart phones, smart televisions, and smart watches) ensures that the end user experience is easy, by connecting lives on web services via the internet. Integrating Internet of Things devices poses ethical risks related to data security, privacy, reliability and management, data mining, and knowledge exchange. An adversarial machine learning attack is a good practice to adopt, to strengthen the security of text-based CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart), to withstand against malicious attacks from computer hackers, to protect Internet of Things devices and the end user’s privacy. The goal of this current study is to perform security vulnerability verification on adversarial text-based CAPTCHA, based on attacker–defender scenarios. Therefore, this study proposed computation-efficient deep learning with a mixed batch adversarial generation process model, which attempted to break the transferability attack, and mitigate the problem of catastrophic forgetting in the context of adversarial attack defense. After performing K-fold cross-validation, experimental results showed that the proposed defense model achieved mean accuracies in the range of 82–84% among three gradient-based adversarial attack datasets. |
| first_indexed | 2024-03-10T09:17:00Z |
| format | Article |
| id | doaj.art-65252738785b4e738baae07ff5ba68d2 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-10T09:17:00Z |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-65252738785b4e738baae07ff5ba68d22023-11-22T05:31:05ZengMDPI AGElectronics2079-92922021-07-011015179810.3390/electronics10151798Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security VerificationStephen Dankwa0Lu Yang1School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611371, ChinaSchool of Automation Engineering, University of Electronic Science and Technology of China, Chengdu 611371, ChinaThe Internet of Things environment (e.g., smart phones, smart televisions, and smart watches) ensures that the end user experience is easy, by connecting lives on web services via the internet. Integrating Internet of Things devices poses ethical risks related to data security, privacy, reliability and management, data mining, and knowledge exchange. An adversarial machine learning attack is a good practice to adopt, to strengthen the security of text-based CAPTCHA (Completely Automated Public Turing test to tell Computers and Humans Apart), to withstand against malicious attacks from computer hackers, to protect Internet of Things devices and the end user’s privacy. The goal of this current study is to perform security vulnerability verification on adversarial text-based CAPTCHA, based on attacker–defender scenarios. Therefore, this study proposed computation-efficient deep learning with a mixed batch adversarial generation process model, which attempted to break the transferability attack, and mitigate the problem of catastrophic forgetting in the context of adversarial attack defense. After performing K-fold cross-validation, experimental results showed that the proposed defense model achieved mean accuracies in the range of 82–84% among three gradient-based adversarial attack datasets.https://www.mdpi.com/2079-9292/10/15/1798securityprivacyIoTartificial intelligenceadversarial machine learningdeep learning |
| spellingShingle | Stephen Dankwa Lu Yang Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification Electronics security privacy IoT artificial intelligence adversarial machine learning deep learning |
| title | Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification |
| title_full | Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification |
| title_fullStr | Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification |
| title_full_unstemmed | Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification |
| title_short | Securing IoT Devices: A Robust and Efficient Deep Learning with a Mixed Batch Adversarial Generation Process for CAPTCHA Security Verification |
| title_sort | securing iot devices a robust and efficient deep learning with a mixed batch adversarial generation process for captcha security verification |
| topic | security privacy IoT artificial intelligence adversarial machine learning deep learning |
| url | https://www.mdpi.com/2079-9292/10/15/1798 |
| work_keys_str_mv | AT stephendankwa securingiotdevicesarobustandefficientdeeplearningwithamixedbatchadversarialgenerationprocessforcaptchasecurityverification AT luyang securingiotdevicesarobustandefficientdeeplearningwithamixedbatchadversarialgenerationprocessforcaptchasecurityverification |