{"id":"W3196544260","doi":"10.1109/trustcom53373.2021.00102","title":"DeepTaskAPT: Insider APT detection using Task-tree based Deep Learning","year":2021,"lang":"en","type":"article","venue":"2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)","topic":"Software System Performance and Reliability","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Computer science; Task (project management); Deep learning; Baseline (sea); Artificial intelligence; Tree (set theory); Machine learning; Construct (python library); Process (computing); Insider threat; Host (biology); Artificial neural network; Data mining; Insider","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00078425,0.001673927,0.0006733435,0.001228184,0.0004147856,0.0009364247,0.001667474,0.001183775,0.001463798],"category_scores_gemma":[0.002327685,0.0003355986,0.0009628311,0.00090691,0.0004005232,0.002361872,0.001625761,0.00197407,0.001106928],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008176733,"about_ca_system_score_gemma":0.001146105,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005893507,"about_ca_topic_score_gemma":0.01079381,"domain_scores_codex":[0.9994715,0.00008863815,0.00003285675,0.0001576707,0.0001401727,0.0001092704],"domain_scores_gemma":[0.999065,0.000248457,0.0001438398,0.0002275105,0.0002162665,0.00009888936],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009343613,0.001448792,0.03904947,0.0005457129,0.0003361728,0.0007143707,0.000298545,0.2684897,0.01482552,0.005385967,0.08541223,0.5825592],"study_design_scores_gemma":[0.00002761319,0.0001754081,0.002894232,0.00002521115,0.0000277926,0.0001500013,0.00005764074,0.979831,0.006044599,0.006157282,0.00458547,0.00002374225],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3534927,0.002318866,0.5903563,0.001531363,0.0005662901,0.0005639317,0.01754348,0.02488631,0.008740828],"genre_scores_gemma":[0.7977118,0.0006437891,0.1592587,0.0007547409,0.0001361321,0.0003352244,0.03150082,0.0003902878,0.009268535],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005893507,"threshold_uncertainty_score":0.01171839,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04747473644529669,"score_gpt":0.3163940392541474,"score_spread":0.2689193028088507,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}