Possibility Theory-Based Approach to Spam Email Detection

Dat Tran; Wanli Ma; Dharmendra Sharma; Thien Nguyen

doi:10.1109/GrC.2007.123

Possibility Theory-Based Approach to Spam Email Detection

Dat Tran, Wanli Ma, Dharmendra Sharma, Thien Nguyen

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

5 Citations (Scopus)

46 Downloads (Pure)

Abstract

Most of current spam email detection systems use keywords in a blacklist to detect spam emails. However these keywords can be written as misspellings, for example "baank", "ba-nk" and "bankk" instead of "bank". Moreover, misspellings are changed from time to time and hence spam email detection system needs to constantly update the blacklist to detect spam emails containing such misspellings. However it is impossible to predict all possible misspellings for a given keyword to add those to the blacklist. We present a possibility theory-based approach to spam email detection to solve this problem. We consider every keyword in the blacklist along with its misspellings as a fuzzy set and propose a possibility function. This function will be used to calculate a possibility score for an unknown email. Using a proposed if-then rule and this core, we can decide whether or not this unknown email is spam. Experimental results are also presented

Original language	English
Title of host publication	2007 IEEE International Conference on Granular Computing (GRC 2007)
Editors	T.Y Lin, X Hu
Place of Publication	United States
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	571-575
Number of pages	5
ISBN (Print)	9780769530321
DOIs	https://doi.org/10.1109/GrC.2007.123
Publication status	Published - 2007
Event	IEEE International Conference on Granular Computing - San Jose, United States Duration: 2 Nov 2007 → 4 Nov 2007

Conference

Conference	IEEE International Conference on Granular Computing
Country/Territory	United States
City	San Jose
Period	2/11/07 → 4/11/07

Access to Document

10.1109/GrC.2007.123

PaperFinal published version, 445 KB

Cite this

@inproceedings{12150ebdaa6c41dcbc8bfc17770d0915,

title = "Possibility Theory-Based Approach to Spam Email Detection",

abstract = "Most of current spam email detection systems use keywords in a blacklist to detect spam emails. However these keywords can be written as misspellings, for example {"}baank{"}, {"}ba-nk{"} and {"}bankk{"} instead of {"}bank{"}. Moreover, misspellings are changed from time to time and hence spam email detection system needs to constantly update the blacklist to detect spam emails containing such misspellings. However it is impossible to predict all possible misspellings for a given keyword to add those to the blacklist. We present a possibility theory-based approach to spam email detection to solve this problem. We consider every keyword in the blacklist along with its misspellings as a fuzzy set and propose a possibility function. This function will be used to calculate a possibility score for an unknown email. Using a proposed if-then rule and this core, we can decide whether or not this unknown email is spam. Experimental results are also presented",

author = "Dat Tran and Wanli Ma and Dharmendra Sharma and Thien Nguyen",

year = "2007",

doi = "10.1109/GrC.2007.123",

language = "English",

isbn = "9780769530321",

pages = "571--575",

editor = "T.Y Lin and X Hu",

booktitle = "2007 IEEE International Conference on Granular Computing (GRC 2007)",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

address = "United States",

note = "IEEE International Conference on Granular Computing ; Conference date: 02-11-2007 Through 04-11-2007",

}

Tran, D , Ma, W , Sharma, D & Nguyen, T 2007, Possibility Theory-Based Approach to Spam Email Detection. in TY Lin & X Hu (eds), 2007 IEEE International Conference on Granular Computing (GRC 2007). IEEE, Institute of Electrical and Electronics Engineers, United States, pp. 571-575, IEEE International Conference on Granular Computing, San Jose, United States, 2/11/07. https://doi.org/10.1109/GrC.2007.123

Possibility Theory-Based Approach to Spam Email Detection. / Tran, Dat ; Ma, Wanli ; Sharma, Dharmendra et al.
2007 IEEE International Conference on Granular Computing (GRC 2007). ed. / T.Y Lin; X Hu. United States: IEEE, Institute of Electrical and Electronics Engineers, 2007. p. 571-575.

Research output: A Conference proceeding or a Chapter in Book › Conference contribution › peer-review

TY - GEN

T1 - Possibility Theory-Based Approach to Spam Email Detection

AU - Tran, Dat

AU - Ma, Wanli

AU - Sharma, Dharmendra

AU - Nguyen, Thien

PY - 2007

Y1 - 2007

N2 - Most of current spam email detection systems use keywords in a blacklist to detect spam emails. However these keywords can be written as misspellings, for example "baank", "ba-nk" and "bankk" instead of "bank". Moreover, misspellings are changed from time to time and hence spam email detection system needs to constantly update the blacklist to detect spam emails containing such misspellings. However it is impossible to predict all possible misspellings for a given keyword to add those to the blacklist. We present a possibility theory-based approach to spam email detection to solve this problem. We consider every keyword in the blacklist along with its misspellings as a fuzzy set and propose a possibility function. This function will be used to calculate a possibility score for an unknown email. Using a proposed if-then rule and this core, we can decide whether or not this unknown email is spam. Experimental results are also presented

AB - Most of current spam email detection systems use keywords in a blacklist to detect spam emails. However these keywords can be written as misspellings, for example "baank", "ba-nk" and "bankk" instead of "bank". Moreover, misspellings are changed from time to time and hence spam email detection system needs to constantly update the blacklist to detect spam emails containing such misspellings. However it is impossible to predict all possible misspellings for a given keyword to add those to the blacklist. We present a possibility theory-based approach to spam email detection to solve this problem. We consider every keyword in the blacklist along with its misspellings as a fuzzy set and propose a possibility function. This function will be used to calculate a possibility score for an unknown email. Using a proposed if-then rule and this core, we can decide whether or not this unknown email is spam. Experimental results are also presented

U2 - 10.1109/GrC.2007.123

DO - 10.1109/GrC.2007.123

M3 - Conference contribution

SN - 9780769530321

SP - 571

EP - 575

BT - 2007 IEEE International Conference on Granular Computing (GRC 2007)

A2 - Lin, T.Y

A2 - Hu, X

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - United States

T2 - IEEE International Conference on Granular Computing

Y2 - 2 November 2007 through 4 November 2007

ER -

Possibility Theory-Based Approach to Spam Email Detection

Abstract

Conference

Access to Document

Fingerprint

Cite this