Local Pixel Attack Based on Sensitive Pixel Location for Remote Sensing Images
As deep neural networks (DNNs) are widely used in the field of remote sensing image recognition, there is a model security issue that cannot be ignored. DNNs have been shown to be vulnerable to small perturbations in a large number of studies in the past, and this security risk naturally exists in r...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/12/9/1987 |
| _version_ | 1797602739919781888 |
|---|---|
| author | Lu Liu Zixuan Xu Daqing He Dequan Yang Hongchen Guo |
| author_facet | Lu Liu Zixuan Xu Daqing He Dequan Yang Hongchen Guo |
| author_sort | Lu Liu |
| collection | DOAJ |
| description | As deep neural networks (DNNs) are widely used in the field of remote sensing image recognition, there is a model security issue that cannot be ignored. DNNs have been shown to be vulnerable to small perturbations in a large number of studies in the past, and this security risk naturally exists in remote sensing object detection models based on DNNs. The complexity of remote sensing object detection models makes it difficult to implement adversarial attacks on them, resulting in the current lack of systematic research on adversarial examples in the field of remote sensing image recognition. In order to better deal with the adversarial threats that remote sensing image recognition models may confront and to provide an effective means for evaluating the robustness of the models, this paper takes the adversarial examples for remote sensing image recognition as the research goal and systematically studies vanishing attacks against a remote sensing image object detection model. To solve the problem of difficult attack implementation on remote sensing image object detection, adversarial attack adaptation methods based on interpolation scaling and patch perturbation stacking are proposed in this paper, which realizes the adaptation of classical attack algorithms. We propose a hot restart perturbation update strategy and the joint attack of the first and second stages of the two-stage remote sensing object detection model is realized through the design of the attack loss function. For the problem of the modification cost of global pixel attack being too large, a local pixel attack algorithm based on sensitive pixel location is proposed in this paper. By searching the location of the sensitive pixels and constructing the mask of attack area, good local pixel attack effect is achieved. Experimental results show that the average pixel modification rate of the proposed attack method decreases to less than 4% and the vanishing rate can still be maintained above 80%, which effectively achieves the balance between attack effect and attack cost. |
| first_indexed | 2024-03-11T04:20:54Z |
| format | Article |
| id | doaj.art-21544527a41c41b0955f3c411c935564 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-11T04:20:54Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-21544527a41c41b0955f3c411c9355642023-11-17T22:47:11ZengMDPI AGElectronics2079-92922023-04-01129198710.3390/electronics12091987Local Pixel Attack Based on Sensitive Pixel Location for Remote Sensing ImagesLu Liu0Zixuan Xu1Daqing He2Dequan Yang3Hongchen Guo4School of Computer Science, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Computer Science, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaInformation Technology Center, Beijing Institute of Technology, Beijing 100081, ChinaSchool of Cyberspace Science and Technology, Beijing Institute of Technology, Beijing 100081, ChinaAs deep neural networks (DNNs) are widely used in the field of remote sensing image recognition, there is a model security issue that cannot be ignored. DNNs have been shown to be vulnerable to small perturbations in a large number of studies in the past, and this security risk naturally exists in remote sensing object detection models based on DNNs. The complexity of remote sensing object detection models makes it difficult to implement adversarial attacks on them, resulting in the current lack of systematic research on adversarial examples in the field of remote sensing image recognition. In order to better deal with the adversarial threats that remote sensing image recognition models may confront and to provide an effective means for evaluating the robustness of the models, this paper takes the adversarial examples for remote sensing image recognition as the research goal and systematically studies vanishing attacks against a remote sensing image object detection model. To solve the problem of difficult attack implementation on remote sensing image object detection, adversarial attack adaptation methods based on interpolation scaling and patch perturbation stacking are proposed in this paper, which realizes the adaptation of classical attack algorithms. We propose a hot restart perturbation update strategy and the joint attack of the first and second stages of the two-stage remote sensing object detection model is realized through the design of the attack loss function. For the problem of the modification cost of global pixel attack being too large, a local pixel attack algorithm based on sensitive pixel location is proposed in this paper. By searching the location of the sensitive pixels and constructing the mask of attack area, good local pixel attack effect is achieved. Experimental results show that the average pixel modification rate of the proposed attack method decreases to less than 4% and the vanishing rate can still be maintained above 80%, which effectively achieves the balance between attack effect and attack cost.https://www.mdpi.com/2079-9292/12/9/1987adversarial examplesremote sensing image object detectionvanishing attack |
| spellingShingle | Lu Liu Zixuan Xu Daqing He Dequan Yang Hongchen Guo Local Pixel Attack Based on Sensitive Pixel Location for Remote Sensing Images Electronics adversarial examples remote sensing image object detection vanishing attack |
| title | Local Pixel Attack Based on Sensitive Pixel Location for Remote Sensing Images |
| title_full | Local Pixel Attack Based on Sensitive Pixel Location for Remote Sensing Images |
| title_fullStr | Local Pixel Attack Based on Sensitive Pixel Location for Remote Sensing Images |
| title_full_unstemmed | Local Pixel Attack Based on Sensitive Pixel Location for Remote Sensing Images |
| title_short | Local Pixel Attack Based on Sensitive Pixel Location for Remote Sensing Images |
| title_sort | local pixel attack based on sensitive pixel location for remote sensing images |
| topic | adversarial examples remote sensing image object detection vanishing attack |
| url | https://www.mdpi.com/2079-9292/12/9/1987 |
| work_keys_str_mv | AT luliu localpixelattackbasedonsensitivepixellocationforremotesensingimages AT zixuanxu localpixelattackbasedonsensitivepixellocationforremotesensingimages AT daqinghe localpixelattackbasedonsensitivepixellocationforremotesensingimages AT dequanyang localpixelattackbasedonsensitivepixellocationforremotesensingimages AT hongchenguo localpixelattackbasedonsensitivepixellocationforremotesensingimages |