### Table 9: Intra and Inter Cluster Distance with Cookies

2000

Cited by 4

### Table 2: Security of cookie authentication mechanisms using legacy browsers and locked cookie browsers. Each cell reports the strongest threat model resisted by each combination of authentication mech- anism and browser type. We consider phishing, pharming, and active attacks (Section 2.1).

2007

### Table 8: Common Clusters between Logs sessionised with and without Cookies

2000

Cited by 4

### Table 10: Intra and Inter Cluster Distance without Cookies

2000

Cited by 4

### Table 3: Meaningful Cluseters obtained without and with use of cookies

2000

"... In PAGE 10: ... Hence, clusters created using cookies are more cohesive than the clusters created using IP addresses. Table3 shows that nearly half the number of clusters obtained in both approaches are common to each other. From Table 1, we can observe that among similar clusters, the intra-cluster distance... ..."

Cited by 4

### Table 7. cluster/term browser built bureau bush

2007

"... In PAGE 6: ...particular term in the full collection of keywords is used in an abstract of one of the cluster submissions, the term frequency for that term in that cluster is incremented by 1. An example feature vector is provided in Table7 . For example, for all the submissions in cluster 3, the term built was used 7 times.... In PAGE 6: .... An example feature vector is provided in Table 7. For example, for all the submissions in cluster 3, the term built was used 7 times. cluster/term browser built bureau bush 3 3 7 3 1 4 4 3 2 0 5 1 0 1 0 Table7 : Cluster feature vectors of the keywords in the submission abstracts For each cluster i it is possible to determine how specific a particular term j is to that cluster according to Eq. 2 where freq(i, j) is the frequency of term j in cluster i, n(i) is the total number of terms in cluster i, N is the number of clusters (which is always 8 for this experiment), and nc(j) is the number of clusters for which term j appears (Salton, 1998).... ..."

Cited by 1

### Table 7. cluster/term browser built bureau bush

2007

"... In PAGE 5: ... Each time a particular term in the full collection of keywords is used in an abstract of one of the cluster submissions, the term frequency for that term in that cluster is incremented by 1. An example feature vector is provided in Table7 . For example, for all the submissions in cluster 3, the term built was used 7 times.... In PAGE 6: ...browser built bureau bush 3 3 7 3 1 4 4 3 2 0 5 1 0 1 0 Table7 : Cluster feature vectors of the keywords in the submission abstracts For each cluster i it is possible to determine how specific a particular term j is to that cluster according to Eq. 2 where freq(i, j) is the frequency of term j in cluster i, n(i) is the total number of terms in cluster i, N is the number of clusters (which is always 8 for this experiment), and nc(j) is the number of clusters for which term j appears (Salton, 1998).... ..."

Cited by 1

### Table 4: CSEE Logs Analysis using Linear FCMdd Algorithm and Cookies Cluster Cardinality URLs URLs Deg

2000

Cited by 4

### Table 5: CSEE Logs Analysis using Linear FCMdd Algorithm and Cookies Cluster Cardinality URLs URLs Deg

2000

Cited by 4

### Table 7: CSEE Logs Analysis using Linear FCMdd Algorithm and without Cookies Cluster Cardinality URLs URLs Deg

2000

Cited by 4