from fastapi import FastAPI import os, random, time, json from fastapi import FastAPI, Query from fastapi.middleware.cors import CORSMiddleware import httpx # ============================================================ # app_spaceB_demo.py — Demo版 Active Learning Space (模擬流程) # ============================================================ # === 全域計數器 === FILE_COUNTER = 0 FILE_THRESHOLD = 1000 # === FastAPI 初始化 === app = FastAPI( title="Malvec Space B (Demo)", description="Simulated Active Learning backend, connected to real Space A.", version="demo-2.0" ) app.add_middleware( CORSMiddleware, allow_origins=["*"], allow_methods=["*"], allow_headers=["*"] ) # === 模擬參數 ===(這邊你可以把它改成你想要的md5) SIMULATED_BRANCHES = ["round_1", "round_2", "round_3"] SIMULATED_FILES = [ "dropper_payload.exe", "trojbanker_loader.exe", "ransom_v2.exe", "spyeye_injector.exe", "worm_autoexec.exe" ] # === Space A 連線設定(請改成你的真實 Space A API endpoint)=== SPACE_A_URL = os.getenv("SPACE_A_URL", "https://malvec-test.hf.space") @app.get("/") def greet_json(): return {"Hello": "World!"} # ============================================================ # 🧠 Endpoint 1️⃣: 模擬 Entropy 決策 # ============================================================ # @app.post("/check-new-samples") # def check_new_samples(entropy_threshold: float = Query(0.9)): # """ # 模擬 Active Learning 決策: # entropy 隨機 → 若高於門檻則要求人工標註; # 否則推薦既有模型分支。 # """ # mean_entropy = round(random.uniform(0.5, 1.5), 3) # print(f"[Demo B] 模擬 mean_entropy={mean_entropy}") # # 高熵 → 模擬需要人工標註 # if mean_entropy > entropy_threshold: # samples = random.sample(SIMULATED_FILES, k=min(3, len(SIMULATED_FILES))) # label_file = f"./demo_selected_for_labeling_{time.strftime('%H%M%S')}.json" # result = { # "status": "need_labeling", # "mean_entropy": mean_entropy, # "samples_to_label": [ # {"source": s, "entropy": round(random.uniform(1.2, 1.8), 3)} for s in samples # ], # "label_file": label_file, # "cached_branches": len(SIMULATED_BRANCHES) # } # print(f"⚠️ 高熵 → 請人工標註: {samples}") # print(result) # return result # # 低熵 → 模擬選擇最佳分支 # else: # branch = random.choice(SIMULATED_BRANCHES) # result = { # "status": "use_existing_model", # "recommended_branch": branch, # "mean_entropy": mean_entropy, # "cached_branches": len(SIMULATED_BRANCHES) # } # print(f"✅ 低熵 → 推薦使用分支: {branch}") # print(result) # return result @app.post("/check-new-samples") def check_new_samples(entropy_threshold: float = Query(0.9)): global FILE_COUNTER # Demo: 每次呼叫視為一個新 sample FILE_COUNTER += 1 print(f"[Demo B] Accumulated samples: {FILE_COUNTER}/{FILE_THRESHOLD}") # 未達 1000 → 只回覆「累積中」 if FILE_COUNTER < FILE_THRESHOLD: return { "status": "accumulating", "received_samples": FILE_COUNTER, "remaining": FILE_THRESHOLD - FILE_COUNTER } # === 達到 1000 隻 → 執行一次 entropy 評估 === FILE_COUNTER = 0 # reset mean_entropy = round(random.uniform(0.5, 1.5), 3) print(f"[Demo B] Batch entropy evaluation: mean_entropy={mean_entropy}") # 高熵(需要人工標註) if mean_entropy > entropy_threshold: samples = random.sample(SIMULATED_FILES, k=min(3, len(SIMULATED_FILES))) label_file = f"./demo_selected_for_labeling_{time.strftime('%H%M%S')}.json" return { "status": "need_labeling", "mean_entropy": mean_entropy, "samples_to_label": [ {"source": s, "entropy": round(random.uniform(1.2, 1.8), 3)} for s in samples ], "label_file": label_file, "cached_branches": len(SIMULATED_BRANCHES), "batch_size": FILE_THRESHOLD } # 低熵(選 existing branch) else: branch = random.choice(SIMULATED_BRANCHES) return { "status": "use_existing_model", "recommended_branch": branch, "mean_entropy": mean_entropy, "cached_branches": len(SIMULATED_BRANCHES), "batch_size": FILE_THRESHOLD } # ============================================================ # 🧩 Endpoint 2️⃣: 模擬人工標註後的訓練 # ============================================================ @app.post("/train-from-labeled") async def train_from_labeled(label_file: str = Query(...)): """ 模擬人工標註完成後自動更新模型(假訓練) 並通知真正的 Space A。 """ print(f"🧠 模擬訓練資料: {label_file}") time.sleep(2.0) tag = f"demo-al-{time.strftime('%H%M%S')}" payload = {"status": "updated", "tag": tag} print(f"📡 通知 Space A: {payload}") try: async with httpx.AsyncClient(timeout=10) as client: resp = await client.post(SPACE_A_URL, json=payload) print(f"✅ Space A 回應: {resp.status_code}") return { "status": "ok", "output_dir": f"./demo_output/{tag}", "tag": tag, "notified_spaceA": True, "spaceA_response": resp.text } except Exception as e: print(f"⚠️ 通知 Space A 失敗: {e}") return { "status": "ok", "output_dir": f"./demo_output/{tag}", "tag": tag, "notified_spaceA": False, "error": str(e) } # ============================================================ # 🧭 Endpoint 3️⃣: 模擬列出快取 LoRA 分支 # ============================================================ @app.get("/list-lora-cache") def list_lora_cache(): branches = [{"branch": b, "num_samples": random.randint(600, 1200)} for b in SIMULATED_BRANCHES] print("[Demo B] 回傳模擬 LoRA 分支列表") return {"status": "ok", "total_branches": len(branches), "branches": branches} # ============================================================ # ❤️ Endpoint 4️⃣: 健康檢查 # ============================================================ @app.get("/health") def health_check(): return { "status": "running", "mode": "demo", "connected_to": SPACE_A_URL, "branches": SIMULATED_BRANCHES }