Filtering Image Spam with Near-Duplicate Detection

121 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

The security of machine learning (2010, background): “Another possibility is to take advantage of a computationally expensive learning component: for example, spam filters that use image processing to detect advertisements in graphical attachments can take significantly more time than text-based filtering (Dredze et al. 2007; Wang et al. 2007).”
A survey of learning-based techniques of email spam filtering (2008, methodology): “[94] use such fast-to-extract features as color histogram, orientation histograms, and coefficients of wavelet transformation of the image.”
A survey and experimental evaluation of image spam filtering techniques (2011, methodology): “This approach is implemented in Wang et al. (2007) by exploiting one or several feature sets, possibly extracted by existing image spam filters (in this case they are used only as feature extractors, not as classifiers).”
A survey of image spamming and filtering techniques (2013, methodology): “Image spam is defined as: the actual spam message is moved into an image attached to the message (Wang et al. 2007; Nhung and Phuong 2007; Krasser et al. 2007; Gargiulo and Sansone 2008), image spam means spam including image which appears in the main body or attachment the main body (He et al.…”
Machine learning for email spam filtering: review, approaches and open research problems (2019, background): “Princeton spam image Benchmark 1071 0 100% 2007 Wang et al [44]”