| Инд. авторы: | Monarev V., Duplischev I., Pestunov A. |
| Заглавие: | Compression-Based Integral Prior Classification for Improving Steganalysis |
| Библ. ссылка: | Monarev V., Duplischev I., Pestunov A. Compression-Based Integral Prior Classification for Improving Steganalysis // Lecture Notes in Computer Science. - 2016. - Vol.9977. - P.134-144. - ISSN 0302-9743. - EISSN 1611-3349. |
| Внешние системы: | DOI: 10.1007/978-3-319-50011-9_11; РИНЦ: 29463982; SCOPUS: 2-s2.0-85005992620; WoS: 000389790900011; |
| Реферат: | eng: We propose the integral prior classification approach for binary steganalysis which imply that several detectors are trained, and each detector is intended for processing only images with certain compression rate. In particular, the training set is splitted into several parts according to the images compression rate, then a corresponding number of detectors are trained, but each detector uses only an ascribed to it subset. The testing images are distributed between the detectors also according to their compression rate. We utilize BOSSbase 1.01 as benchmark data along with HUGO, WOW and S-UNIWARD as benchmark embedding algorithms. Comparison with state-of-the-art results demonstrated that, depending on the case, the integral prior classification allows to decrease the detection error by 0.05-0.16. |
| Ключевые слова: | SRM; Prior classification; WOW; UNIWARD; PSRM; Compression; Support vector machine; Steganalysis; Information hiding; HUGO; |
| Издано: | 2016 |
| Физ. характеристика: | с.134-144 |
| Конференция: | Название: 18th International Conference on Information and Communications Security Аббревиатура: ICICS-2016 Город: Singapore Страна: Singapore Даты проведения: 2016-11-29 - 2016-12-02 Ссылка: http://www.springer.com/in/book/9783319500102 |
