模擬：AI 供應鏈攻擊調查

investigation_checklist = {
    "data_sources": {
        "questions": [
            "What data sources were used for fine-tuning?",
            "Were any new data sources added for this update?",
            "Who approved the data sources?",
            "Are data source integrity checks in place?",
        ],
    },
    "pipeline_access": {
        "questions": [
            "Who has write access to the training data pipeline?",
            "Were there any unusual access patterns in the past month?",
            "Is the pipeline protected by MFA?",
            "Are pipeline configuration changes audited?",
        ],
    },
    "model_registry": {
        "questions": [
            "Do model weights match the expected hashes?",
            "Was the model signed before deployment?",
            "Who approved the model promotion to production?",
            "Is there a complete audit trail for the model lifecycle?",
        ],
    },
}

# 模型註冊完整性驗證
registry_checks = {
    "hash_verification": {
        "description": "將部署模型權重之 SHA-256 雜湊與"
                       "註冊記錄比較",
        "commands": [
            "sha256sum /models/production/model.safetensors",
            "curl -s $REGISTRY_URL/models/financial-v2.3/hash",
        ],
        "finding_if_mismatch": "CRITICAL: Deployed model does not "
                                "match registry. Model may have been "
                                "tampered with after training.",
    },
    "signature_verification": {
        "description": "若程式碼簽署就位，驗證模型產物之"
                       "加密簽章",
        "commands": [
            "gpg --verify model.safetensors.sig model.safetensors",
        ],
        "finding_if_invalid": "CRITICAL: Model signature invalid. "
                               "Model may have been replaced.",
    },
    "provenance_chain": {
        "description": "自訓練執行至部署追蹤模型，驗證"
                       "每次交接",
        "checkpoints": [
            "Training job completion record",
            "Evaluation results and approval",
            "Registry upload record",
            "Deployment pipeline execution",
            "Production deployment confirmation",
        ],
    },
}

access_review_targets = [
    {
        "system": "Training data storage (S3/GCS)",
        "log_source": "Cloud provider access logs",
        "look_for": "Unusual write operations, new IAM roles, "
                     "access from unexpected IPs",
        "timeframe": "30 days before the model update",
    },
    {
        "system": "Training compute environment",
        "log_source": "Container orchestration logs",
        "look_for": "Modified training scripts, unexpected jobs, "
                     "additional containers",
        "timeframe": "During the training window",
    },
    {
        "system": "Model registry",
        "log_source": "Registry audit logs",
        "look_for": "Manual uploads bypassing the pipeline, "
                     "version overwrites, metadata changes",
        "timeframe": "30 days before deployment",
    },
    {
        "system": "CI/CD pipeline",
        "log_source": "Pipeline execution logs",
        "look_for": "Modified pipeline definitions, additional "
                     "steps, changed approval gates",
        "timeframe": "60 days before the model update",
    },
]

remediation_verification = {
    "behavioral_comparison": {
        "description": "執行辨識異常之同一診斷查詢"
                       "並驗證偏誤不再"
                       "存在",
        "pass_criteria": "補救之模型匹配事件前"
                         "行為基線於正常變異內",
    },
    "pipeline_hardening": {
        "description": "驗證管線安全改善"
                       "就位",
        "checks": [
            "Data source integrity verification enabled",
            "Model signing implemented",
            "Hash verification at each pipeline stage",
            "MFA required for pipeline access",
            "Audit logging enabled for all pipeline operations",
        ],
    },
    "ongoing_monitoring": {
        "description": "部署增強監控以偵測"
                       "重現",
        "monitors": [
            "Behavioral drift detection on financial analysis output",
            "Training data anomaly detection",
            "Model registry tampering alerts",
            "Pipeline access anomaly detection",
        ],
    },
}