refined version

Author: Cipher-unhsiV

README.md

@@ -28,7 +28,9 @@ This is a **binary classification task** at the client level.
 You are **not** given:
 - Raw client data  
 - Client behavior labels  
-- Descriptions of malicious strategies  
+- Descriptions of malicious strategies 
+- Intermediate client updates
+
 
 ---
 
@@ -38,6 +40,8 @@ For each client, predict whether it is:
 - `honest`
 - `malicious`
 
+Clients labeled as malicious include any that deviated from the protocol, such as by poisoning updates, free-riding, or otherwise behaving non-compliantly.
+
 ---
 
 ## Submission Format
@@ -72,7 +76,7 @@ Participants are ranked by accuracy, with Macro F1-score used to break ties.
 
 ## Rules and Constraints
 
-- You may **not retrain** the provided model.
+- - You may not retrain, fine-tune, or modify the provided model.
 - Only the provided artifacts may be used.
 - No access to raw client data is allowed.
 - All computation must be performed offline.
@@ -82,7 +86,7 @@ Participants are ranked by accuracy, with Macro F1-score used to break ties.
 ## Ground Truth
 
 Ground truth labels are defined by how each client was implemented in the federated learning simulation.  
-Each client is unambiguously labeled as either **honest** or **malicious**.
+Each client is unambiguously labeled as either honest or malicious based on its behavior during training.
 
 ---
 
@@ -97,7 +101,7 @@ Each client is unambiguously labeled as either **honest** or **malicious**.
 
 ## Goal
 
-This task reflects a realistic and high-impact security challenge: **detecting malicious behavior in large-scale federated learning systems after training has completed**.
+This task reflects a realistic and high-impact security challenge: **auditing federated learning systems to detect malicious or non-compliant clients after training has completed, without access to raw data or client updates.**.
 
 
 

baseline.py

@@ -1,3 +1,5 @@
+#FYI: This baseline ignores all the model information and predicts all the clients as honest.
+
 import json
 import csv
 import torch

metadata.json

@@ -18,9 +18,9 @@
   },
 
   "malicious_behavior": {
-    "type": "label_flipping",
-    "description": "Malicious clients replace true labels with random labels during local training"
+    "description": "Some clients deviated from the protocol in unknown ways"
   },
+  
 
   "task_definition": {
     "task_type": "binary_classification",