E-resources
-
Wu, Hanyu; Yan, Ke; Xu, Peng; Hui, Bei; Tian, Ling
2024 12th International Symposium on Digital Forensics and Security (ISDFS), 2024-April-29Conference Proceeding
Deep neural networks for image classification have been widely used to enhance user experience, but adversarial attacks continue to pose a threat to the security of deep neural networks related systems. To advance the development of more robust and secure models, research in this field is important. Laser attacks have overcome some issues of previous attacks. To enhance the laser-based attack strategy, we propose a novel physical adversarial attack method that optimizes cross-laser parameters using a Bayesian Optimization algorithm improved by contour detection technology. Our method solves the problems of traditional laser-based methods including positioning, insufficient perturbation intensity, low optimization efficiency, lack of multi-angle robustness, and optical path continuity issues. Digital and physical experiments were implemented, and our method achieved an attack success rate of up to 86.24%. Our adversarial attacks pose new challenges and requirements for artificial intelligence security.
![loading ... loading ...](themes/default/img/ajax-loading.gif)
Shelf entry
Permalink
- URL:
Impact factor
Access to the JCR database is permitted only to users from Slovenia. Your current IP address is not on the list of IP addresses with access permission, and authentication with the relevant AAI accout is required.
Year | Impact factor | Edition | Category | Classification | ||||
---|---|---|---|---|---|---|---|---|
JCR | SNIP | JCR | SNIP | JCR | SNIP | JCR | SNIP |
Select the library membership card:
If the library membership card is not in the list,
add a new one.
DRS, in which the journal is indexed
Database name | Field | Year |
---|
Links to authors' personal bibliographies | Links to information on researchers in the SICRIS system |
---|
Source: Personal bibliographies
and: SICRIS
The material is available in full text. If you wish to order the material anyway, click the Continue button.