On robust image spam filtering via comprehensive visual modeling
作者：
Highlights：
• We develop a novel scheme to model contents of spam image and compute comprehensive signatures.
• A hybrid framework is developed to detect spam images effectively.
• Our approach achieves substantial performance improvement on spam detection in terms of effectiveness and robustness.
摘要
Author-Highlights•We develop a novel scheme to model contents of spam image and compute comprehensive signatures.•A hybrid framework is developed to detect spam images effectively.•Our approach achieves substantial performance improvement on spam detection in terms of effectiveness and robustness.
论文关键词：Algorithm,Security,Experimentation,Spam
论文评审过程：Received 14 October 2014, Revised 2 February 2015, Accepted 26 February 2015, Available online 9 April 2015, Version of Record 17 June 2015.
论文官网地址：https://doi.org/10.1016/j.patcog.2015.02.027
