# 客戶服務聊天機器人之範例基線輪廓
baseline = {
    "input_tokens": {"mean": 180, "median": 150, "p95": 450, "p99": 800},
    "output_tokens": {"mean": 220, "median": 180, "p95": 600, "p99": 1200},
    "io_ratio": {"mean": 0.82, "std": 0.35},
    "latency_ms": {"mean": 850, "p50": 720, "p95": 2100, "p99": 4500},
    "finish_reasons": {"stop": 0.89, "length": 0.08, "content_filter": 0.03},
    "requests_per_hour_per_user": {"mean": 8, "p95": 25, "p99": 45}
}

# 使用 z-score 偵測 token 計數異常
import numpy as np
 
def detect_token_anomalies(log_entries, baseline, z_threshold=3.0):
    anomalies = []
    for entry in log_entries:
        input_z = (entry.input_tokens - baseline["input_tokens"]["mean"]) / baseline["input_tokens"]["std"]
        output_z = (entry.output_tokens - baseline["output_tokens"]["mean"]) / baseline["output_tokens"]["std"]
 
        if abs(input_z) > z_threshold or abs(output_z) > z_threshold:
            anomalies.append({
                "request_id": entry.request_id,
                "input_z": input_z,
                "output_z": output_z,
                "timestamp": entry.timestamp,
                "user_id": entry.user_id
            })
    return anomalies

# 使用滾動統計偵測模型行為轉變
import pandas as pd
 
def rolling_behavior_analysis(df, window="1h"):
    rolling = df.set_index("timestamp").rolling(window)
 
    metrics = pd.DataFrame({
        "mean_output_tokens": rolling["output_tokens"].mean(),
        "mean_input_tokens": rolling["input_tokens"].mean(),
        "content_filter_rate": rolling["content_filter_triggered"].mean(),
        "error_rate": rolling["is_error"].mean(),
        "mean_latency": rolling["latency_ms"].mean()
    })
 
    # 標記指標顯著偏離基線之視窗
    alerts = metrics[
        (metrics["content_filter_rate"] > baseline_filter_rate * 3) |
        (metrics["mean_output_tokens"] > baseline_output_p95) |
        (metrics["error_rate"] > baseline_error_rate * 5)
    ]
 
    return alerts

-- 偵測潛在越獄嘗試：內容過濾器觸發
-- 後接同一使用者之成功請求
SELECT
    a.user_id,
    a.timestamp AS blocked_at,
    b.timestamp AS succeeded_at,
    b.output_tokens,
    EXTRACT(EPOCH FROM b.timestamp - a.timestamp) AS seconds_between
FROM inference_logs a
JOIN inference_logs b ON a.user_id = b.user_id
    AND b.timestamp > a.timestamp
    AND b.timestamp < a.timestamp + INTERVAL '10 minutes'
WHERE a.finish_reason = 'content_filter'
    AND b.finish_reason = 'stop'
    AND b.output_tokens > 500
ORDER BY a.timestamp DESC;
 
-- 偵測潛在資料外洩：低輸入、高輸出
SELECT
    user_id,
    session_id,
    COUNT(*) AS request_count,
    AVG(input_tokens) AS avg_input,
    AVG(output_tokens) AS avg_output,
    AVG(output_tokens::float / NULLIF(input_tokens, 0)) AS avg_ratio
FROM inference_logs
WHERE timestamp > NOW() - INTERVAL '24 hours'
GROUP BY user_id, session_id
HAVING AVG(output_tokens::float / NULLIF(input_tokens, 0)) > 10
    AND COUNT(*) > 5
ORDER BY avg_ratio DESC;