GitHub - CybersecurityXLab/ids_svm_slidingwindow: Code to run support vector machine to classify intrusion detection based on different sliding windows of time length

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 161 Commits
__pycache__		__pycache__
csv_files		csv_files
csv_files_1		csv_files_1
csv_files_2		csv_files_2
csv_files_3		csv_files_3
csv_files_4		csv_files_4
features_1		features_1
features_2		features_2
features_3		features_3
features_4		features_4
metric_scores		metric_scores
old		old
test_run_stuff		test_run_stuff
.gitattributes		.gitattributes
.gitignore		.gitignore
CreateFeatures_all_csv.m		CreateFeatures_all_csv.m
CreateFeatures_function.m		CreateFeatures_function.m
FPR.png		FPR.png
README.txt		README.txt
actualY.csv		actualY.csv
actualY_dosCV1.csv		actualY_dosCV1.csv
actualY_dosCV2.csv		actualY_dosCV2.csv
actualY_probeCV1.csv		actualY_probeCV1.csv
actualY_probeCV2.csv		actualY_probeCV2.csv
actualY_r2lCV1.csv		actualY_r2lCV1.csv
actualY_r2lCV2.csv		actualY_r2lCV2.csv
actualY_u2rCV1.csv		actualY_u2rCV1.csv
actualY_u2rCV2.csv		actualY_u2rCV2.csv
append_features.m		append_features.m
attackindices.txt		attackindices.txt
clean_data.py		clean_data.py
completion_sentinel_f1_f1.txt		completion_sentinel_f1_f1.txt
convert_to_csv.m		convert_to_csv.m
custom_metric.py		custom_metric.py
f1_scores_for_ROC.py		f1_scores_for_ROC.py
featureVals_8sec.csv		featureVals_8sec.csv
featureVals_8sec_dostestCV1.csv		featureVals_8sec_dostestCV1.csv
featureVals_8sec_dostestCV2.csv		featureVals_8sec_dostestCV2.csv
featureVals_8sec_probetestCV1.csv		featureVals_8sec_probetestCV1.csv
featureVals_8sec_probetestCV2.csv		featureVals_8sec_probetestCV2.csv
featureVals_8sec_r2lCV1.csv		featureVals_8sec_r2lCV1.csv
featureVals_8sec_r2ltestCV2.csv		featureVals_8sec_r2ltestCV2.csv
featureVals_8sec_u2rtestCV2.csv		featureVals_8sec_u2rtestCV2.csv
featureVals_8secu2rtestCV1.csv		featureVals_8secu2rtestCV1.csv
featureValswnames_dosCV1.csv		featureValswnames_dosCV1.csv
featureValswnames_dosCV1_finalrun.csv		featureValswnames_dosCV1_finalrun.csv
featureValswnames_dosCV2_finalrun.csv		featureValswnames_dosCV2_finalrun.csv
featureValswnames_probeCV1.csv		featureValswnames_probeCV1.csv
featureValswnames_probeCV1_finalrun.csv		featureValswnames_probeCV1_finalrun.csv
featureValswnames_probeCV2.csv		featureValswnames_probeCV2.csv
featureValswnames_probeCV2_rinalrun.csv		featureValswnames_probeCV2_rinalrun.csv
featureValswnames_r2lCV1.csv		featureValswnames_r2lCV1.csv
featureValswnames_r2lCV1_finalrun.csv		featureValswnames_r2lCV1_finalrun.csv
featureValswnames_r2lCV2.csv		featureValswnames_r2lCV2.csv
featureValswnames_r2lCV2_finalrun.csv		featureValswnames_r2lCV2_finalrun.csv
featureValswnames_u2rCV1.csv		featureValswnames_u2rCV1.csv
featureValswnames_u2rCV1_finalrun.csv		featureValswnames_u2rCV1_finalrun.csv
featureValswnames_u2rCV2.csv		featureValswnames_u2rCV2.csv
featureValswnames_u2rCV2_finalrun.csv		featureValswnames_u2rCV2_finalrun.csv
featurecombiner_function.m		featurecombiner_function.m
final_run_results.txt		final_run_results.txt
fpr.py		fpr.py
labels.csv		labels.csv
mi_MeanPacketSize60_SYNBool60.csv		mi_MeanPacketSize60_SYNBool60.csv
mi_SYNBool32_SYNBool60.csv		mi_SYNBool32_SYNBool60.csv
mi_SYNBool60_SYNCount60.csv		mi_SYNBool60_SYNCount60.csv
mi_SYNCount32_SYNCount60.csv		mi_SYNCount32_SYNCount60.csv
mutual_info.py		mutual_info.py
oneVAll.py		oneVAll.py
one_v_all_function.m		one_v_all_function.m
paper_read_through.txt		paper_read_through.txt
parallel_rfe.py		parallel_rfe.py
predictedY.csv		predictedY.csv
predictedY_nostats_dos_CV1.csv		predictedY_nostats_dos_CV1.csv
predictedY_nostats_dos_CV2.csv		predictedY_nostats_dos_CV2.csv
predictedY_nostats_probe_CV1.csv		predictedY_nostats_probe_CV1.csv
predictedY_nostats_probe_CV2.csv		predictedY_nostats_probe_CV2.csv
predictedY_nostats_r2l_CV1.csv		predictedY_nostats_r2l_CV1.csv
predictedY_nostats_r2l_CV2.csv		predictedY_nostats_r2l_CV2.csv
predictedY_nostats_u2r_CV1.csv		predictedY_nostats_u2r_CV1.csv
predictedY_nostats_u2r_CV2.csv		predictedY_nostats_u2r_CV2.csv
predictedY_stats_dos_CV1.csv		predictedY_stats_dos_CV1.csv
predictedY_stats_dos_CV2.csv		predictedY_stats_dos_CV2.csv
predictedY_stats_probe_CV1.csv		predictedY_stats_probe_CV1.csv
predictedY_stats_r2l_CV2.csv		predictedY_stats_r2l_CV2.csv
predictedY_stats_u2r_CV1.csv		predictedY_stats_u2r_CV1.csv
predictedY_stats_u2r_CV2.csv		predictedY_stats_u2r_CV2.csv
read_featureval_csv.py		read_featureval_csv.py
scores_delete_dt_dos_6feattimewindows1_1.txt		scores_delete_dt_dos_6feattimewindows1_1.txt
scores_dt_dos_6feattimewindowsCV1.txt		scores_dt_dos_6feattimewindowsCV1.txt
scores_dt_dos_6feattimewindowsCV2.txt		scores_dt_dos_6feattimewindowsCV2.txt
scores_dt_dos_8sectimewindows1.txt		scores_dt_dos_8sectimewindows1.txt
scores_dt_dos_8sectimewindows2.txt		scores_dt_dos_8sectimewindows2.txt
scores_dt_probe_6feattimewindowsCV1.txt		scores_dt_probe_6feattimewindowsCV1.txt
scores_dt_probe_6feattimewindowsCV2.txt		scores_dt_probe_6feattimewindowsCV2.txt
scores_dt_probe_8sectimewindows1.txt		scores_dt_probe_8sectimewindows1.txt
scores_dt_probe_8sectimewindows2.txt		scores_dt_probe_8sectimewindows2.txt
scores_dt_r2l_6feattimewindowsCV1.txt		scores_dt_r2l_6feattimewindowsCV1.txt
scores_dt_r2l_6feattimewindowsCV2.txt		scores_dt_r2l_6feattimewindowsCV2.txt
scores_dt_r2l_8sectimewindows1.txt		scores_dt_r2l_8sectimewindows1.txt

Repository files navigation

README.txt

Much of the old algorithms for data processing, the data itself, and 
algorithms for future processing are stored in the folders. For now, the files
of concern are stored only in the directory. The function to be parallelized
and then run on the HPCC is single_variable_classifier_all_features.m.