Defense against adversarial attacks in traffic sign images identification based on 5G
Abstract In the past decade, artificial intelligence and Internet of things (IoT) technology have been rapid development, gradually began to integrate with each other, especially in coming 5G era. Admittedly, image recognition is the key technology due to a huge number of video cameras integrated in...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2020-09-01
|
| Series: | EURASIP Journal on Wireless Communications and Networking |
| Subjects: | |
| Online Access: | http://link.springer.com/article/10.1186/s13638-020-01775-5 |
| _version_ | 1829499022176419840 |
|---|---|
| author | Fei Wu Limin Xiao Wenxue Yang Jinbin Zhu |
| author_facet | Fei Wu Limin Xiao Wenxue Yang Jinbin Zhu |
| author_sort | Fei Wu |
| collection | DOAJ |
| description | Abstract In the past decade, artificial intelligence and Internet of things (IoT) technology have been rapid development, gradually began to integrate with each other, especially in coming 5G era. Admittedly, image recognition is the key technology due to a huge number of video cameras integrated in intelligent IoT equipment, such as driverless cars. However, the rapidly growing body of research in adversarial machine learning has demonstrated that the deep learning architectures are vulnerable to adversarial examples. Thus, the raises questions about the security of intelligent Internet of thing (IoT) and trust sensitive areas. This emphasizes the urgent need for practical defense technology that can be deployed to real-time combat attacks at any time. Well-crafted small perturbations lead to the misclassification of legitimate images by neural networks, but not the human visual system. It is worth noting that many attack strategies are designed to disrupt image pixels in a visually imperceptible manner. Therefore, we propose a new defense method and take full advantage of 5G high-speed bandwidth and mobile edge computing (MEC) effectively. We use singular value decomposition (SVD) which is the optimal approximation of matrix in the sense of square loss to eliminate the perturbation. We have conducted extensive and large-scale experiments with German Traffic Sign Recognition Benchmark (GTSRB) datasets and the results show that adversarial attacks, such as Carlini-Wagner’s l 2, Deepfool, and I-FSGM, can be better eliminated by the method and provide lower latency. |
| first_indexed | 2024-12-16T08:24:26Z |
| format | Article |
| id | doaj.art-2497dcc4abd34cc7bfc5aa931fb12fa8 |
| institution | Directory Open Access Journal |
| issn | 1687-1499 |
| language | English |
| last_indexed | 2024-12-16T08:24:26Z |
| publishDate | 2020-09-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | EURASIP Journal on Wireless Communications and Networking |
| spelling | doaj.art-2497dcc4abd34cc7bfc5aa931fb12fa82022-12-21T22:38:01ZengSpringerOpenEURASIP Journal on Wireless Communications and Networking1687-14992020-09-012020111510.1186/s13638-020-01775-5Defense against adversarial attacks in traffic sign images identification based on 5GFei Wu0Limin Xiao1Wenxue Yang2Jinbin Zhu3School of Computer Science and Engineering, Beihang UniversitySchool of Computer Science and Engineering, Beihang UniversitySchool of Computer Science and Engineering, Beihang UniversitySchool of Computer Science and Engineering, Beihang UniversityAbstract In the past decade, artificial intelligence and Internet of things (IoT) technology have been rapid development, gradually began to integrate with each other, especially in coming 5G era. Admittedly, image recognition is the key technology due to a huge number of video cameras integrated in intelligent IoT equipment, such as driverless cars. However, the rapidly growing body of research in adversarial machine learning has demonstrated that the deep learning architectures are vulnerable to adversarial examples. Thus, the raises questions about the security of intelligent Internet of thing (IoT) and trust sensitive areas. This emphasizes the urgent need for practical defense technology that can be deployed to real-time combat attacks at any time. Well-crafted small perturbations lead to the misclassification of legitimate images by neural networks, but not the human visual system. It is worth noting that many attack strategies are designed to disrupt image pixels in a visually imperceptible manner. Therefore, we propose a new defense method and take full advantage of 5G high-speed bandwidth and mobile edge computing (MEC) effectively. We use singular value decomposition (SVD) which is the optimal approximation of matrix in the sense of square loss to eliminate the perturbation. We have conducted extensive and large-scale experiments with German Traffic Sign Recognition Benchmark (GTSRB) datasets and the results show that adversarial attacks, such as Carlini-Wagner’s l 2, Deepfool, and I-FSGM, can be better eliminated by the method and provide lower latency.http://link.springer.com/article/10.1186/s13638-020-01775-5Traffic signsAdversary attacks5GDefenseDeep learning |
| spellingShingle | Fei Wu Limin Xiao Wenxue Yang Jinbin Zhu Defense against adversarial attacks in traffic sign images identification based on 5G EURASIP Journal on Wireless Communications and Networking Traffic signs Adversary attacks 5G Defense Deep learning |
| title | Defense against adversarial attacks in traffic sign images identification based on 5G |
| title_full | Defense against adversarial attacks in traffic sign images identification based on 5G |
| title_fullStr | Defense against adversarial attacks in traffic sign images identification based on 5G |
| title_full_unstemmed | Defense against adversarial attacks in traffic sign images identification based on 5G |
| title_short | Defense against adversarial attacks in traffic sign images identification based on 5G |
| title_sort | defense against adversarial attacks in traffic sign images identification based on 5g |
| topic | Traffic signs Adversary attacks 5G Defense Deep learning |
| url | http://link.springer.com/article/10.1186/s13638-020-01775-5 |
| work_keys_str_mv | AT feiwu defenseagainstadversarialattacksintrafficsignimagesidentificationbasedon5g AT liminxiao defenseagainstadversarialattacksintrafficsignimagesidentificationbasedon5g AT wenxueyang defenseagainstadversarialattacksintrafficsignimagesidentificationbasedon5g AT jinbinzhu defenseagainstadversarialattacksintrafficsignimagesidentificationbasedon5g |