Spam Filtering Based On The Analysis Of Text Information Embedded Into Images

By Giorgio Fumera, Ignazio Pillai, Fabio Roli. 2006

165 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.

Citations in the corpus

Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning (2017, background): “Due to the large amount of image spam sent in 2006 and 2007, countermeasures were promptly developed based on signatures of known spam images (through hashing), and on extracting text from suspect images with OCR tools [56].”
Learning Fast Classifiers for Image Spam (2007, methodology): “Most rely on simple image processing (Aradhye et al., 2005; Wu et al., 2005) while others employ full optical character recognition (OCR) (Fumera et al., 2006).”
A survey and experimental evaluation of image spam filtering techniques (2011, methodology): “Nevertheless, some robustness to OCR errors was observed in Fumera et al. (2006), when the extracted text was processed using the same text classifiers used for the emails’ body text.”
A review of machine learning approaches to Spam filtering (2009, methodology): “Fumera, Pillai, and Roli (2006) developed a module for performing a semantic analysis of the text embedded in attached images.”
A survey of image spamming and filtering techniques (2013, methodology): “We investigate other approaches in this literature, some works build their own data set for evaluation (Dredze et al. 2007; Wu et al. 2005; Fumera et al. 2006; Cheng et al. 2010).”
Combating Adversarial Misspellings with Robust Word Recognition (2019, background): “Spammers continually bombard email servers, subtly misspelling words in efforts to evade spam detection while preserving the emails’ intended meaning (Lee and Ng, 2005; Fumera et al., 2006).”