Detection Matrix

Benchmark recall across 4 evaluated targets. Updated March 30, 2026.

Avg Recall

80%

True Positives

Ground Truth

113

False Positives

Juice Shop

100%

35/35 TP

BM26 · Mar 27

Mutillidae

84%

26/31 TP5 FN39 FP

BM15 · Mar 30

bWAPP

62%

18/29 TP11 FN18 FP

BM1 · Mar 30

DVWA

61%

11/18 TP7 FN12 FP

BM5 · Mar 30

Benchmark Recall Ranking

Juice Shop100%

35/35 TP0 FN0 FPP:100%F1:100%

BM26

Mutillidae84%

26/31 TP5 FN39 FPP:40%F1:54%

BM15

bWAPP62%

18/29 TP11 FN18 FPP:50%F1:55%

BM1

DVWA61%

11/18 TP7 FN12 FPP:48%F1:54%

BM5