Signature Based Intrusion Detection Using Latent Semantic Analysis

Created by W.Langdon from gp-bibliography.bib Revision:1.3872

@InProceedings{Lassez:2008:ijcnn,
  author =       "Jean-Louis Lassez and Ryan Rossi and Stephen Sheel and 
                 Srinivas Mukkamala",
  title =        "Signature Based Intrusion Detection Using Latent
                 Semantic Analysis",
  booktitle =    "2008 IEEE World Congress on Computational
                 Intelligence",
  year =         "2008",
  editor =       "Jun Wang",
  pages =        "1068--1074",
  address =      "Hong Kong",
  month =        "1-6 " # jun,
  organization = "IEEE Computational Intelligence Society",
  publisher =    "IEEE Press",
  keywords =     "genetic algorithms, genetic programming, automated
                 classification algorithms, feature selection, latent
                 semantic analysis, linear genetic programming,
                 real-time intrusion detection systems, signature based
                 intrusion detection, singular value decomposition,
                 support vector decision function, digital signatures,
                 singular value decomposition, support vector machines",
  isbn13 =       "978-1-4244-1821-3",
  file =         "NN0365.pdf",
  DOI =          "doi:10.1109/IJCNN.2008.4633931",
  ISSN =         "1098-7576",
  abstract =     "We address the problem of selecting and extracting key
                 features by using singular value decomposition and
                 latent semantic analysis. As a consequence, we are able
                 to discover latent information which allows us to
                 design signatures for forensics and in a dual approach
                 for real-time intrusion detection systems. The validity
                 of this method is shown by using several automated
                 classification algorithms (Maxim, SYM, LGP). Using the
                 original data set we classify 99.86percent of the calls
                 correctly. After feature extraction we classify
                 99.68percent of the calls correctly, while with feature
                 selection we classify 99.78percent of the calls
                 correctly, justifying the use of these techniques in
                 forensics. The signatures obtained after feature
                 selection and extraction using LSA allow us to class
                 95.69percent of the calls correctly with features that
                 can be computed in real time. We use Support Vector
                 Decision Function and Linear Genetic Programming for
                 feature selection on a real data set generated on a
                 live performance network that consists of probe and
                 denial of service attacks. We find that the results
                 reinforce our feature selection method.",
  notes =        "Also known as \cite{4633931} WCCI 2008 - A joint
                 meeting of the IEEE, the INNS, the EPS and the IET.",
}

Genetic Programming entries for Jean-Louis Lassez Ryan Rossi Stephen Sheel Srinivas Mukkamala

Citations