Adversarial attack application analytics in machine learning
Machine learning is one of the most widely studied and applied technologies, but it is itself vulnerable to attack and its algorithms have the risk of privacy leakage. In this article, through the experts currently popular speech recognition scene, reveals how to build the antagonism against data, m...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
EDP Sciences
2022-01-01
|
| Series: | ITM Web of Conferences |
| Subjects: | |
| Online Access: | https://www.itm-conferences.org/articles/itmconf/pdf/2022/07/itmconf_cccar2022_01005.pdf |
| _version_ | 1811226843695546368 |
|---|---|
| author | Zhang Hongsheng |
| author_facet | Zhang Hongsheng |
| author_sort | Zhang Hongsheng |
| collection | DOAJ |
| description | Machine learning is one of the most widely studied and applied technologies, but it is itself vulnerable to attack and its algorithms have the risk of privacy leakage. In this article, through the experts currently popular speech recognition scene, reveals how to build the antagonism against data, make its differences with the source data is subtle, so much so that humans can’t through sensory recognition, and machine learning model can accept and the classification of making the wrong decision, at the same time made attack, finally prospects the study model to research the development and application of security and privacy protection. |
| first_indexed | 2024-04-12T09:31:42Z |
| format | Article |
| id | doaj.art-ca5dc8e78c684edc8d1f7a1600420879 |
| institution | Directory Open Access Journal |
| issn | 2271-2097 |
| language | English |
| last_indexed | 2024-04-12T09:31:42Z |
| publishDate | 2022-01-01 |
| publisher | EDP Sciences |
| record_format | Article |
| series | ITM Web of Conferences |
| spelling | doaj.art-ca5dc8e78c684edc8d1f7a16004208792022-12-22T03:38:21ZengEDP SciencesITM Web of Conferences2271-20972022-01-01470100510.1051/itmconf/20224701005itmconf_cccar2022_01005Adversarial attack application analytics in machine learningZhang Hongsheng0School of Computing, Wuhan Qingchuan UniversityMachine learning is one of the most widely studied and applied technologies, but it is itself vulnerable to attack and its algorithms have the risk of privacy leakage. In this article, through the experts currently popular speech recognition scene, reveals how to build the antagonism against data, make its differences with the source data is subtle, so much so that humans can’t through sensory recognition, and machine learning model can accept and the classification of making the wrong decision, at the same time made attack, finally prospects the study model to research the development and application of security and privacy protection.https://www.itm-conferences.org/articles/itmconf/pdf/2022/07/itmconf_cccar2022_01005.pdfmachine learningprivacy threatsadversarial attacks |
| spellingShingle | Zhang Hongsheng Adversarial attack application analytics in machine learning ITM Web of Conferences machine learning privacy threats adversarial attacks |
| title | Adversarial attack application analytics in machine learning |
| title_full | Adversarial attack application analytics in machine learning |
| title_fullStr | Adversarial attack application analytics in machine learning |
| title_full_unstemmed | Adversarial attack application analytics in machine learning |
| title_short | Adversarial attack application analytics in machine learning |
| title_sort | adversarial attack application analytics in machine learning |
| topic | machine learning privacy threats adversarial attacks |
| url | https://www.itm-conferences.org/articles/itmconf/pdf/2022/07/itmconf_cccar2022_01005.pdf |
| work_keys_str_mv | AT zhanghongsheng adversarialattackapplicationanalyticsinmachinelearning |