Title PageTable of ContentsAbstract1. Introduction2. Bayes’ Theorem3. Bayesian Spam Filters3.1 SpamBayes3.2 POPFile3.3 Experimental ResultsTable 3.1 Test Record Table 3.2 Breakdown of classification Table 3.3 Test results in confusion Matrices Table 3.4 Confusion matrix Table 3.5 Test results in accuracy, precision, and recall3.4 Evaluation of Bayesian Spam Filters 4. Vulnerabilities5. New Trends in Attacks against Bayesian Spam Filters5.1 Image SpamFigure 5.1 Actual image spam (available at http://www.seas.upenn.edu/~mdredze/datasets/image_spam/)5.2 Image Spam with Content Obfuscation Techniques Figure 5.2 the same image as Figure 5.1 with a speckle added in the lower left corner. Figure 5.3 Content obfuscation techniques used to confuse OCR [26]Figure 5.4 Image spam that is difficult for OCR to read [28]6. Other Spam Filtering Strategies7. ConclusionReferences:Title PageCMPT 585: Intranet and Internet SecurityFall 2008Montclair State UniversityComputing Security ProjectProject Topic: Bayesian Spam Detection Mechanisms and Future of Anti-Spam Filters Project member: Hiroki YamakawaSupervisor: Dr. Stefan A. RobilaTable of ContentsTitle Page ......................................................................................................................... 1 Table of Contents ............................................................................................................. 2 Abstract ............................................................................................................................ 3 1. Introduction .................................................................................................................. 4 2. Bayes’ Theorem ........................................................................................................... 5 3. Bayesian Spam Filters .................................................................................................. 7 3.1 SpamBayes ............................................................................................................. 7 3.2 POPFile .................................................................................................................. 8 3.3 Experimental Results ............................................................................................. 8 3.4 Evaluation of Bayesian Spam Filters .................................................................. 12 4. Vulnerabilities ............................................................................................................ 13 5. New Trends in Attacks against Bayesian Spam Filters ............................................. 14 5.1 Image Spam ......................................................................................................... 14 5.2 Image Spam with Content Obfuscation Techniques ............................................ 15 6. Other Spam Filtering Strategies ................................................................................. 17 7. Conclusion ................................................................................................................. 18 References: ..................................................................................................................... 19 Tables and FiguresTable 3.1 Test Record ..................................................................................................... 9 Table 3.2 Breakdown of classification ............................................................................. 9 Table 3.3 Test results in confusion Matrices ................................................................... 9 Table 3.4 Confusion matrix .......................................................................................... 10 Table 3.5 Test results in accuracy, precision, and recall ............................................... 11 Figure 5.1 Actual image spam ....................................................................................... 14 Figure 5.2 the same image as Figure 5.1 with a speckle. ............................................... 15 Figure 5.3 Content obfuscation techniques used to confuse OCR ................................. 15 Figure 5.4 Image spam that is difficult for OCR to read ............................................... 16 2AbstractA number of spam filtering techniques have been developed to tackle the problems associated with spam emails, such as decreased productivity among employees and compromised computer security caused by malicious mails. Among the pack of filtering techniques, Bayesian spam filters have gained popularity and credibility as one of the most effective ways to detect spam emails. This paper first reviews a probability theory, “Bayes’ Theorem,” which is the backbone of Bayesian spam filters. With this theorem, Bayesian spam filters statistically analyze the text content of emails and generate the probability values for the emails to be spam. Two Bayesian spam filters, SpamBayes and POPFiles, are analyzed in detail, and the experiment conducted to evaluate their spam filtering performance supports the widely-reported effectiveness of Bayesian spam filters.There are some known vulnerabilities in Bayesian spam filters against certain spam tricks. One of the recent and most troubling spam tricks against Bayesian spam filters is called “image spam.” Some techniques used by image spam are studied alongside the vulnerabilities of Bayesian spam filters. Other spam filtering techniques, such as email header verification, are reviewed to show a number of possibilities in spam filtering approaches. They can compliment, or compensate for the vulnerabilities of Bayesian spam filters.31. IntroductionSince the Internet and E-mail became major media of communication in nearly every aspect of our life in the late 1990’s and early 2000’s, they have revolutionized the way of doing business and socializing. The Internet has, just to list a few examples, made information gathering and publishing easy, and has provided the convenience of online shopping and financial management. E-mail has also brought about many