Learning Fast Classifiers for Image Spam

175 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 and experimental evaluation of image spam filtering techniques (2011, methodology): “Manipulating the metadata features proposed in Dredze et al. (2007),Uemura and Tabata (2008) may be even simpler than low-level image features.”
A survey of image spamming and filtering techniques (2013, background): “A non spam image is more likely to have a wider range of colors (Dredze et al. 2007).”
Machine learning for email spam filtering: review, approaches and open research problems (2019, methodology): “Dredze image spam Dataset 3297 2021 62% 2007 Dredze, gevaryahu and elias-bachrach [45]”
A review of machine learning approaches to Spam filtering (2009, methodology): “It was verified that the features proposed in Aradhye et al. (2005) and Dredze et al. (2007) along with the generic ones, led to better results than the obfuscation-sensitive, as the latter tends be reactive to noise typical of legitimate images.”