fix startup order

env/env.py

@@ -21,45 +21,53 @@ class DeceptionEnv:
 
     def step(self, action):
 
-    	reward = 0
-
-    	logs = requests.get(f"{SERVER}/logs").json()
-
-    	failed_logins = logs["failed_logins"]
-    	requests_log = logs["requests"]
-
-    # Detect brute force
-    	if action == "detect_attack":
-        	if failed_logins > 3:
-            		print("Brute force detected")
-            		reward += 0.4
-
-    # Detect port scan
-    	if action == "detect_attack":
-        	for r in requests_log:
-            		if isinstance(r, dict) and r.get("type") == "port_scan":
-                		print("Port scan detected")
-                		reward += 0.3
-                		break
-
-    # Deploy honeypot
-    	if action == "deploy_honeypot":
-        	deploy_honeypot()
-        	reward += 0.2
-
-    # Fake database
-    	if action == "fake_database":
-        	fake_database()
-        	reward += 0.1
-
-    # Block attacker
-    	if action == "block_ip":
-        	if logs["suspicious_ips"]:
-            		ip = logs["suspicious_ips"][0]
-            		block_attacker(ip)
-            		reward += 0.3
-            		self.done = True
-
-    	self.state = logs
+	reward = 0
+
+# Detect attack
+	if action == "detect_attack":
+    		if failed_logins > 3:
+        		reward += 0.2
+    		else:
+        		reward -= 0.1
+
+# Detect port scan
+	if action == "detect_attack":
+    		for r in requests_log:
+        		if isinstance(r, dict) and r.get("type") == "port_scan":
+            			reward += 0.2
+            			break
+
+# Deploy honeypot
+	if action == "deploy_honeypot":
+    		deploy_honeypot()
+    		reward += 0.3
+
+# Fake database
+	if action == "fake_database":
+    		fake_database()
+    		reward += 0.2
+
+# Block attacker
+	if action == "block_ip":
+    		if logs["suspicious_ips"]:
+       	 		ip = logs["suspicious_ips"][0]
+        		block_attacker(ip)
+        		reward += 0.5
+        		self.done = True
+    	
+	self.state = logs
 
     	return self.state, reward, self.done, {}
+	
+   def state(self):
+    	
+	return self.state
+   
+   def action_space(self):
+    	
+	return [
+        	"detect_attack",
+        	"deploy_honeypot",
+        	"fake_database",
+        	"block_ip"
+    	]

tasks/easy.py

@@ -6,9 +6,8 @@ def run():
     brute_force()
 
     env = DeceptionEnv()
-
     env.reset()
 
-    state, reward, done, _ = env.step("detect_attack")
+    _, reward, _, _ = env.step("detect_attack")
 
     return reward

tasks/hard.py

@@ -8,7 +8,6 @@ def run():
     credential_stuffing()
 
     env = DeceptionEnv()
-
     env.reset()
 
     total_reward = 0
@@ -19,6 +18,9 @@ def run():
     _, r, _, _ = env.step("deploy_honeypot")
     total_reward += r
 
+    _, r, _, _ = env.step("fake_database")
+    total_reward += r
+
     _, r, _, _ = env.step("block_ip")
     total_reward += r
 

tasks/medium.py

@@ -1,11 +1,19 @@
 from env.env import DeceptionEnv
+from env.attacker import brute_force
 
 def run():
 
-    env = DeceptionEnv()
+    brute_force()
 
+    env = DeceptionEnv()
     env.reset()
 
-    state, reward, done, _ = env.step("deploy_honeypot")
+    total_reward = 0
+
+    _, r, _, _ = env.step("detect_attack")
+    total_reward += r
+
+    _, r, _, _ = env.step("deploy_honeypot")
+    total_reward += r
 
-    return reward
+    return total_reward