Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015

Chinese Spam Filter under Adversarial Impact

Authors
Yaqing Zhao, Yan Xu, Xiaodan Zhao
Corresponding Author
Yaqing Zhao
Available Online December 2015.
DOI
https://doi.org/10.2991/icmmcce-15.2015.562How to use a DOI?
Keywords
Anti-spam, Machine Learning, Adversarial Attacks, Adversarial Impact
Abstract
Machining learning techniques have achieved great success in anti-spam area. But because of the limitations of these techniques, classifiers derived from them often get attacked by spam senders thus posing a threat to the whole Spam filtering system. This article briefly describes the type of attacks to classifiers and then simulates an attack on a public Chinese spam corpus to analyze the adversarial impact of several major classifiers.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Cite this article

TY  - CONF
AU  - Yaqing Zhao
AU  - Yan Xu
AU  - Xiaodan Zhao
PY  - 2015/12
DA  - 2015/12
TI  - Chinese Spam Filter under Adversarial Impact
BT  - Proceedings of the 4th International Conference on Mechatronics, Materials, Chemistry and Computer Engineering 2015
PB  - Atlantis Press
SN  - 2352-538X
UR  - https://doi.org/10.2991/icmmcce-15.2015.562
DO  - https://doi.org/10.2991/icmmcce-15.2015.562
ID  - Zhao2015/12
ER  -