Figure 11.
A five-panel plot depicts feature contribution trajectories to model output values, shown across panels A, B, C, D, and E.The image depicts five panels labelled A, B, C, D, and E, each showing ranked feature contribution trajectories plotted against model output value on the X-axis. The Y-axis in each panel lists network traffic features such as L 7 P r o t o, Protocol, Client T C P Flags, Shortest Flow P K T, Longest Flow P K T, Max I P P K T Len, Num P K T S Up To 128 Bytes, Num P K T S 128 To 256 Bytes, S r c To D s t Avg Throughput, S r c To D s t Second Bytes, D s t To S r c Second Bytes, T C P Win Max In, T C P Win Max Out, In Bytes, Out Bytes, Duration In, Flow Duration Milliseconds, L 4 S r c Port, L 4 D s t Port, In P K T S, Out P K T S, Server T C P Flags, Min I P P K T Len, and Max T T L, with numeric values shown beside each label. Multiple overlapping curves in each panel depict how feature contributions vary across negative and positive model output values. Each panel uses a different contribution range and scale, illustrating distinct feature influence patterns while maintaining a consistent feature structure across all five panels.

SHAP decision: global graph for NF-ToN-IoT-v2 data set for multiple class category (a–e) – benign, DDoS, DoS, reconnaissance, theft, respectively

or Create an Account

Close Modal
Close Modal