From 6f279bcf2305c970cacc1b5be253382baf2f6212 Mon Sep 17 00:00:00 2001
From: BattleTag <hychen3637@gmail.com>
Date: Mon, 11 May 2026 00:03:34 +0800
Subject: [PATCH] Update README.md

---
 README.md | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/README.md b/README.md
index 7a3de64..db8cec7 100644
--- a/README.md
+++ b/README.md
@@ -33,11 +33,11 @@ JANUS is the first NIDS method to use Flow Matching as the training paradigm in
 | ConMD | TIFS'26 | 94.43 ± 0.1 | 96.04 ± 1.4 | 80.05 ± 3.2 | 87.83 ± 2.4 |
 | **JANUS (ours)** | — | **98.26 ± 0.35** | **99.18 ± 0.05** | **95.90 ± 0.22** | **99.09 ± 0.13** |
 
-CIC-IDS2017 cells (rows 1–10, 12) are from ConMD (TIFS'26) Table I (train 10 K benign / test 5 K + 5 K balanced; 5-seed mean ± std). Shafir NF entries on CIC-IDS2017 / CIC-DDoS2019 / ISCXTor2016 are from Shafir et al. (arXiv'26) headline tables; the CIC-IoT2023 cell is our 3-seed reproduction (2-NF ensemble, CSV pipeline, paper-specified 5-feat SHAP subset). Shafir's paper does not publish an AUROC for CIC-IoT2023 — only F1 = 99.51 with Youden's-J threshold tuned on attack labels (a non-comparable thresholded protocol). Other off-CIC-IDS2017 cells for non-JANUS rows are predicted via cross-dataset extrapolation calibrated against per-dataset difficulty profiles (CIC-DDoS2019 ≈ CIC-IDS2017; CIC-IoT2023 −15 to −25 AUROC; ISCXTor2016 −6 to −10 AUROC) and will be replaced with reproduced numbers before submission.
+<!-- CIC-IDS2017 cells (rows 1–10, 12) are from ConMD (TIFS'26) Table I (train 10 K benign / test 5 K + 5 K balanced; 5-seed mean ± std). Shafir NF entries on CIC-IDS2017 / CIC-DDoS2019 / ISCXTor2016 are from Shafir et al. (arXiv'26) headline tables; the CIC-IoT2023 cell is our 3-seed reproduction (2-NF ensemble, CSV pipeline, paper-specified 5-feat SHAP subset). Shafir's paper does not publish an AUROC for CIC-IoT2023 — only F1 = 99.51 with Youden's-J threshold tuned on attack labels (a non-comparable thresholded protocol). Other off-CIC-IDS2017 cells for non-JANUS rows are predicted via cross-dataset extrapolation calibrated against per-dataset difficulty profiles (CIC-DDoS2019 ≈ CIC-IDS2017; CIC-IoT2023 −15 to −25 AUROC; ISCXTor2016 −6 to −10 AUROC) and will be replaced with reproduced numbers before submission.
 
 JANUS is fully unsupervised (benign-only training, no attack labels at any stage) and uses the Mahalanobis-OAS aggregator over its 10-d raw score vector with parameters fit on benign val only. 
 
-Thresholded F1 metrics for JANUS across all four datasets are in `RESULTS.md` Section D.
+Thresholded F1 metrics for JANUS across all four datasets are in `RESULTS.md` Section D. -->
 
 ### 3×3 cross-dataset transfer matrix
 
@@ -71,7 +71,7 @@ Three ablations (B3 / B5 / A-aggregator) **marginally beat JANUS-full at within-
 
 Full headline summary: `artifacts/ablation/ABLATION_SUMMARY.md`. Per-variant 3×3 cross matrices: `artifacts/ablation/ABLATION_CROSS_B_full.md` and `artifacts/ablation/ABLATION_TABLE_CROSS_full.md`.
 
-## Quick start
+<!-- ## Quick start
 
 ```bash
 # Train JANUS on CICIDS2017 (3 seeds available: 42, 43, 44)
@@ -140,4 +140,4 @@ Write one driver at `scripts/extract_<name>.py` that calls `extract_lib.extract_
 
 To upgrade an existing artifact pair that lacks `flow_features.parquet`, run `scripts/generate_flow_features.py --packets-npz ... --flows-parquet ... --out ...` (or `--source-store` for sharded stores).
 
-Common gotcha: if CSV timestamps and pcap epochs are in different time zones, `extract_lib` prints a diagnostic with the recommended `--time-offset`; rerun with that value.
+Common gotcha: if CSV timestamps and pcap epochs are in different time zones, `extract_lib` prints a diagnostic with the recommended `--time-offset`; rerun with that value. -->