← pcfic.com
LAMINAR
LIVE DEMO
Pacific Platform · Claims 27, 28, 62–66

Structural Network Intrusion Detection
via PCF Signature Vectors

Network flows are converted to token sequences and analyzed via structural signatures. Dual-signal OR classifier: Signal A (structural distance exceeds calibrated detection threshold) OR Signal B (attack-token fraction exceeds calibrated detection threshold). No signature database. No training data.

F1 0.969
BruteForce
F1 0.949
DDoS
~1.5ms
Per trace
CPU · CICIDS2017
Benchmark
How It Works
Step 1
Flow Metering
Network flows → 5 CICFlowMeter features: packets/sec, packet length mean, flow duration, fwd/bwd packet counts. No DPI required.
Step 2
Tokenize
flow_to_tokens() maps features to security vocabulary. 10 token types encode behavioral semantics of network activity.
AUTH_BRUTE · NET_FLOOD · NET_PORTSCAN
NET_SLOW_CONN · NET_LARGE_SEND · NET_SEND
NET_RECV · NET_CONNECT · SYS_READ · SYS_WRITE
Step 3
Dual-Signal OR
Signal A: structural distance exceeds calibrated detection threshold derived from benign calibration traces. Signal B: attack-token fraction exceeds calibrated detection threshold of benign baseline. Intrusion detected if A OR B.
Step 4
Alert
Attack type classified from token distribution. Confidence, structural distance from benign baseline, and structural divergence all reported in the alert.
Live Alert Feed · 1,280 real detections · CICIDS2017 · is_real_data: true
Recent Detections
Loading…
Loading real detections…