Distributed classification for image spam detection

Amiza Amir, Bala Srinivasan, Asad I. Khan

    Research output: Contribution to journalArticleResearchpeer-review

    Abstract

    Spam appears in various forms and the current trend in spamming is moving towards multimedia spam objects. Image spam is a new type of spam attacks which attempts to bypass the spam filters that mostly text-based. Spamming attacks the users in many ways and these are usually countered by having a server to filter the spammers. This paper provides a fully-distributed pattern recognition system within P2P networks using the distributed associative memory tree (DASMET) algorithm to detect spam which is cost-efficient and not prone to a single point of failure, unlike the server-based systems. This algorithm is scalable for large and frequently updated data sets, and specifically designed for data sets that consist of similar occurring patterns.We have evaluated our system against centralised state-of-the-art algorithms (NN, k-NN, naive Bayes, BPNN and RBFN) and distributed P2P-based algorithms (Ivote-DPV, ensemble k-NN, ensemble naive Bayes, and P2P-GN). The experimental results show that our method is highly accurate with a 98 to 99% accuracy rate, and incurs a small number of messages—in the best-case, it requires only two messages per recall test. In summary, our experimental results show that the DAS-MET performs best with a relatively small amount of resources for the spam detection compared to other distributed methods.

    LanguageEnglish
    Pages13249-13278
    Number of pages30
    JournalMultimedia Tools and Applications
    Volume77
    Issue number11
    DOIs
    Publication statusPublished - Jun 2018

    Keywords

    • Distributed classification
    • Distributed data mining
    • Distributed pattern recognition
    • Image spam
    • P2P classification
    • P2P data mining
    • Spam detection

    Cite this

    Amir, Amiza ; Srinivasan, Bala ; Khan, Asad I. / Distributed classification for image spam detection. In: Multimedia Tools and Applications. 2018 ; Vol. 77, No. 11. pp. 13249-13278.
    @article{8a1ca8795b464cdc84bccd5a4d4645f5,
    title = "Distributed classification for image spam detection",
    abstract = "Spam appears in various forms and the current trend in spamming is moving towards multimedia spam objects. Image spam is a new type of spam attacks which attempts to bypass the spam filters that mostly text-based. Spamming attacks the users in many ways and these are usually countered by having a server to filter the spammers. This paper provides a fully-distributed pattern recognition system within P2P networks using the distributed associative memory tree (DASMET) algorithm to detect spam which is cost-efficient and not prone to a single point of failure, unlike the server-based systems. This algorithm is scalable for large and frequently updated data sets, and specifically designed for data sets that consist of similar occurring patterns.We have evaluated our system against centralised state-of-the-art algorithms (NN, k-NN, naive Bayes, BPNN and RBFN) and distributed P2P-based algorithms (Ivote-DPV, ensemble k-NN, ensemble naive Bayes, and P2P-GN). The experimental results show that our method is highly accurate with a 98 to 99{\%} accuracy rate, and incurs a small number of messages—in the best-case, it requires only two messages per recall test. In summary, our experimental results show that the DAS-MET performs best with a relatively small amount of resources for the spam detection compared to other distributed methods.",
    keywords = "Distributed classification, Distributed data mining, Distributed pattern recognition, Image spam, P2P classification, P2P data mining, Spam detection",
    author = "Amiza Amir and Bala Srinivasan and Khan, {Asad I.}",
    year = "2018",
    month = "6",
    doi = "10.1007/s11042-017-4944-y",
    language = "English",
    volume = "77",
    pages = "13249--13278",
    journal = "Multimedia Tools and Applications",
    issn = "1380-7501",
    publisher = "Springer-Verlag London Ltd.",
    number = "11",

    }

    Distributed classification for image spam detection. / Amir, Amiza; Srinivasan, Bala; Khan, Asad I.

    In: Multimedia Tools and Applications, Vol. 77, No. 11, 06.2018, p. 13249-13278.

    Research output: Contribution to journalArticleResearchpeer-review

    TY - JOUR

    T1 - Distributed classification for image spam detection

    AU - Amir, Amiza

    AU - Srinivasan, Bala

    AU - Khan, Asad I.

    PY - 2018/6

    Y1 - 2018/6

    N2 - Spam appears in various forms and the current trend in spamming is moving towards multimedia spam objects. Image spam is a new type of spam attacks which attempts to bypass the spam filters that mostly text-based. Spamming attacks the users in many ways and these are usually countered by having a server to filter the spammers. This paper provides a fully-distributed pattern recognition system within P2P networks using the distributed associative memory tree (DASMET) algorithm to detect spam which is cost-efficient and not prone to a single point of failure, unlike the server-based systems. This algorithm is scalable for large and frequently updated data sets, and specifically designed for data sets that consist of similar occurring patterns.We have evaluated our system against centralised state-of-the-art algorithms (NN, k-NN, naive Bayes, BPNN and RBFN) and distributed P2P-based algorithms (Ivote-DPV, ensemble k-NN, ensemble naive Bayes, and P2P-GN). The experimental results show that our method is highly accurate with a 98 to 99% accuracy rate, and incurs a small number of messages—in the best-case, it requires only two messages per recall test. In summary, our experimental results show that the DAS-MET performs best with a relatively small amount of resources for the spam detection compared to other distributed methods.

    AB - Spam appears in various forms and the current trend in spamming is moving towards multimedia spam objects. Image spam is a new type of spam attacks which attempts to bypass the spam filters that mostly text-based. Spamming attacks the users in many ways and these are usually countered by having a server to filter the spammers. This paper provides a fully-distributed pattern recognition system within P2P networks using the distributed associative memory tree (DASMET) algorithm to detect spam which is cost-efficient and not prone to a single point of failure, unlike the server-based systems. This algorithm is scalable for large and frequently updated data sets, and specifically designed for data sets that consist of similar occurring patterns.We have evaluated our system against centralised state-of-the-art algorithms (NN, k-NN, naive Bayes, BPNN and RBFN) and distributed P2P-based algorithms (Ivote-DPV, ensemble k-NN, ensemble naive Bayes, and P2P-GN). The experimental results show that our method is highly accurate with a 98 to 99% accuracy rate, and incurs a small number of messages—in the best-case, it requires only two messages per recall test. In summary, our experimental results show that the DAS-MET performs best with a relatively small amount of resources for the spam detection compared to other distributed methods.

    KW - Distributed classification

    KW - Distributed data mining

    KW - Distributed pattern recognition

    KW - Image spam

    KW - P2P classification

    KW - P2P data mining

    KW - Spam detection

    UR - http://www.scopus.com/inward/record.url?scp=85021752441&partnerID=8YFLogxK

    U2 - 10.1007/s11042-017-4944-y

    DO - 10.1007/s11042-017-4944-y

    M3 - Article

    VL - 77

    SP - 13249

    EP - 13278

    JO - Multimedia Tools and Applications

    T2 - Multimedia Tools and Applications

    JF - Multimedia Tools and Applications

    SN - 1380-7501

    IS - 11

    ER -