Using visual features for anti-spam filtering

@inproceedings{citeulike:1154281, abstract = {Unsolicited commercial email (UCE), also known as spam, has been a major problem on the Internet. In the past, researchers have addressed this problem as a text classification or categorization problem. However, as spammers' techniques continue to evolve and the genre of email content becomes more and more diverse, text-based anti-spam approaches alone are no longer sufficient. In this paper, we propose a novel anti-spam system which utilizes visual clues, in addition to text information in the email body, to determine whether a message is spam. We analyze a large collection of spam emails containing images and identify a number of useful visual features for this application. We then propose using one-class support vector machines (SVM) as the underlying base classifier for anti-spam filtering. The experimental results demonstrate that the proposed system can add significant filtering power to the existing text-based anti-spam filters.}, author = {Wu, Ching-Tung and Cheng, Kwang-Ting and Zhu, Qiang and Wu, Yi-Leh }, booktitle = {IEEE International Conference on Image Processing}, citeulike-article-id = {1154281}, doi = {http://dx.doi.org/10.1109/ICIP.2005.1530440}, journal = {IEEE International Conference on Image Processing, 2005. ICIP 2005. IEEE International Conference on}, keywords = {image-processing, occ-applications, occ-support-vector}, pages = {509--512}, posted-at = {2007-03-11 16:34:10}, priority = {2}, title = {Using visual features for anti-spam filtering}, url = {http://dx.doi.org/10.1109/ICIP.2005.1530440}, volume = {3}, year = {2005} }

TY - CONF ID - citeulike:1154281 L3 - citeulike-article-id:1154281 TI - Using visual features for anti-spam filtering T2 - IEEE International Conference on Image Processing JF - IEEE International Conference on Image Processing, 2005. ICIP 2005. IEEE International Conference on VL - 3 SP - 509 EP - 512 N2 - Unsolicited commercial email (UCE), also known as spam, has been a major problem on the Internet. In the past, researchers have addressed this problem as a text classification or categorization problem. However, as spammers' techniques continue to evolve and the genre of email content becomes more and more diverse, text-based anti-spam approaches alone are no longer sufficient. In this paper, we propose a novel anti-spam system which utilizes visual clues, in addition to text information in the email body, to determine whether a message is spam. We analyze a large collection of spam emails containing images and identify a number of useful visual features for this application. We then propose using one-class support vector machines (SVM) as the underlying base classifier for anti-spam filtering. The experimental results demonstrate that the proposed system can add significant filtering power to the existing text-based anti-spam filters. KW - image-processing KW - occ-applications KW - occ-support-vector AU - Wu, Ching-Tung AU - Cheng, Kwang-Ting AU - Zhu, Qiang AU - Wu, Yi-Leh PY - 2005/// UR - http://dx.doi.org/10.1109/ICIP.2005.1530440 ER -