2013
DOI: 10.1016/j.eswa.2013.01.008
|View full text |Cite
|
Sign up to set email alerts
|

Optimising anti-spam filters with evolutionary algorithms

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

0
16
0
1

Year Published

2014
2014
2021
2021

Publication Types

Select...
5
4

Relationship

4
5

Authors

Journals

citations
Cited by 29 publications
(17 citation statements)
references
References 15 publications
0
16
0
1
Order By: Relevance
“…In previous work on anti-SPAM filter optimization [46] it was observed that many rules were not participating in the classification process and some (with very small weights) only marginally influenced the classification results. This observation suggests that in addition to optimizing fpr and fnr, the complexity of the anti-SPAM filter or its parsimony can be optimized.…”
Section: A Spam Multiobjective Problem Formulationmentioning
confidence: 99%
See 1 more Smart Citation
“…In previous work on anti-SPAM filter optimization [46] it was observed that many rules were not participating in the classification process and some (with very small weights) only marginally influenced the classification results. This observation suggests that in addition to optimizing fpr and fnr, the complexity of the anti-SPAM filter or its parsimony can be optimized.…”
Section: A Spam Multiobjective Problem Formulationmentioning
confidence: 99%
“…SPAM filtering problem optimization has been addressed by the techniques surveyed in [45], [46]. The formulation of the scores setting optimization problem is naturally bi-objective, a typical user would wish to minimize both, the number of SPAM messages not identified by anti-spam filtering techniques, called false negative rate (fnr), and the number of legitimate messages classified as SPAM by mistake, called false positive rate (fpr).…”
Section: A Spam Multiobjective Problem Formulationmentioning
confidence: 99%
“…Moreover, we also believe that our WSF2 framework can take advantage from URI Blacklists (URIBL), commonly used in the e-mail filtering domain. In addition to the obvious technical development, we believe that the use of different filter optimization heuristics (e.g., tuning up rule scores, finding and removing irrelevant features, or detecting counterproductive rules) would be very appropriate to complement the current state of the art [51][52][53][54]. Finally, the lack of effective tools for web spam dataset management and maintenance also suggests an interesting option for future research activities.…”
Section: Discussionmentioning
confidence: 99%
“…In this context, and given the extensive utilization and increasing significance of rule-based filtering frameworks for the anti-spam domain, several studies have addressed the optimization of parameters (rule scores and scheduling plan) to improve their accuracy [4,5,6,7] and classification throughput [8,9,10]. However, previous works on throughput optimization are based on simple heuristics without taking into account its relation to accuracy.…”
Section: Introductionmentioning
confidence: 99%