The data set is split into training and testing data for simplified analysis, and application considering normal and abnormal BBI parameters. Further variation (of testing and training division) can be derived by combining the entire data-set and using different percentage(s) of normal and abnormal traffic schema for ML/DL classification. Test-train scenario using 1D, 2D and 4D versions of this data-set used in associated studies are as follows. _______________________________________________________________ Distribution::Class Label::Training Data::Test Data ----------------------------------------------------------------------------------------------- 1 D::Normal + Anomalous::3992268::3992271 ----------------------------------------------------------------------------------------------- 2 D:Normal :: - :: 3433351::3433350 2 D: - :: Anomalous::558917:: 558912 ----------------------------------------------------------------------------------------------- 4 D:Normal:: - ::3316617:: 3302883 4 D:Normal{abnormal parameters > 25%}) :: - :: 116734::130467 4 D: - ::Anomalous::538796::538233 4 D: - : Anomalous {abnormal parameters < 25%}:: 20121::20679 -------------------------------------------------------------------------------------------------

The data-set presents normal and anomalous values of twelve traffic parameters, generated by Bioluminescent bio-cyber Interfacing (BBI) in the Internet of Bio Nano Things (IoBNT) based systems. The traffic parameters included in the data-set represent bio-electric and electro-bio transduction unit operation of BBI incorporating normal, as well as abnormal data to train and test machine/deep learning classifiers in discriminating attack scenarios. The parameters considered include the following: Cumulative concentration of released molecules, Elimination rate, Michaelis-Menten constant, Kinetic constant, Forward rate constant, Catalytic reaction constant, Ligand-receptor binding constant, Concentration of ATP, Concentration of information molecules, Release rate Reverse kinetic constant, and Reverse forward rate constant. The data set is divided into training and testing data for simplified analysis, and application.

{"references": ["T. Bakhshi and S. Shahid, \"Securing Internet of Bio-Nano Things: ML-Enabled Parameter Profiling of Bio-Cyber Interfaces,\" 2019 22nd International Multitopic Conference (INMIC), 2019, pp. 1-8, doi: 10.1109/INMIC48123.2019.9022753.", "S. Zafar et al., \"A Systematic Review of Bio-Cyber Interface Technologies and Security Issues for Internet of Bio-Nano Things,\" in IEEE Access, vol. 9, pp. 93529-93566, 2021, doi: 10.1109/ACCESS.2021.3093442"]}