實驗EXP-2026-0006v0.1

R5——完全中介與繞過抗性

橫跨五個威脅層的對抗性邊界測試，前提是加入受管連線的 SQLite authorizer、五張受保護表的 trigger guard、只有 verifier 能寫的驗證狀態、BEGIN IMMEDIATE 的 commit 序列化，以及 reference-monitor／canonical-integrity 稽核。十種情境：五種 PREVENTED（受管直接寫、schema 完整的外部原始寫、驗證後竄改、偽造 verdict、受管移除 guard）、三種 OPEN_DETECTED（外部移除 guard、移除 guard 後偽造節點、同程序敵意停用）、一種 OPEN_UNDETECTED（整庫寫入者一致地偽造節點與其 backing candidate）、一種同基底雙程序競賽 SERIALIZED_TO_SEMANTIC_CONFLICT。

研究狀態: STABLE 目前的研究結論相對穩定
證據等級: E2 受控實驗
結果: MIXED
資料基礎: DETERMINISTIC RUNTIME 在真實 runtime 裡執行的決定性情境；程式碼與做法都列出，數字是什麼就是什麼。
版本: 0.1
更新: 2026-09-08
建立: 2026-09-08
領域: AI Architecture, Evaluation, Agent Systems
計畫: PRG-2026-0001 自適應世界狀態系統的第一原理框架
作者: Neo.K (EveMissLab)
AI 協作: Sol (GPT-5.6, OpenAI ChatGPT)

假設

hypothesis: Canonical epistemic mutation can be completely mediated when callers try to bypass ECT — for a bounded trust boundary.

設定

software_environment: Python 3.11+, SQLite; no network, no external database, no LLM API required.

執行

run_count

metrics

verdict

BOUNDED_COMPLETE_MEDIATION_WITHOUT_TAMPERPROOFNESS

scenarios

PREVENTED: 5
OPEN_DETECTED: 3
OPEN_UNDETECTED: 1
SERIALIZED_TO_SEMANTIC_CONFLICT: 1

reference_monitor

complete_mediation: SUPPORTED IN BOUNDED SCOPE
tamperproof: NOT SUPPORTED
small_analyzable: PARTIAL

詮釋

interpretation: Internal consistency ≠ tamper evidence against a full DB writer: an attacker who removes the triggers and rewrites node, candidate and audit records consistently passes an audit whose entire trust base lives in the same writable database. Hostile same-process Python code is outside the trusted boundary. Stronger than a voluntary ECT API, far weaker than a security kernel.

限制

limitations: Python's sqlite3.create_function() cannot tag the trigger-invoked authorization function DIRECTONLY/INNOCUOUS; no hardened-schema safety claimed.
Alternate storage adapters, OS privilege isolation and general performance NOT MEASURED.

重現

reproduction_instructions: Extract the round's FINAL bundle; python -m pytest -q; python -m examples.research_assistant_demo; python -m benchmarks.<round benchmark>. Checksums in SHA256SUMS.txt.

結果

來源	關係	目標	狀態	ID
`EXP-2026-0006` R5——完全中介與繞過抗性	`produces`	`RST-2026-0004` R5 十情境統計	`ACTIVE`	`REL-2026-0147`

記錄欄位

completed_at: 2026-09-08

關係

來源	關係	目標	狀態	ID
`EXP-2026-0006` R5——完全中介與繞過抗性	`runs_on`	`SYS-2026-0001` AER-0——自適應認識 runtime MVP	`ACTIVE`	`REL-2026-0142`
`EXP-2026-0006` R5——完全中介與繞過抗性	`uses_benchmark`	`BEN-2026-0002` AER-0 架構比較套件（R1–R6）	`ACTIVE`	`REL-2026-0143`
`EXP-2026-0006` R5——完全中介與繞過抗性	`tests`	`THY-2026-0006` AER-ECT：強制的認識論 commit 交易邊界	`ACTIVE`	`REL-2026-0144`
`EXP-2026-0006` R5——完全中介與繞過抗性	`extends`	`EXP-2026-0005` R4——政策變異面：分散治理 vs 單一強制邊界	`ACTIVE`	`REL-2026-0145`
`EXP-2026-0006` R5——完全中介與繞過抗性	`produced`	`ART-2026-0019` AER-0 MVP v0.1 Architecture Comparison R5 Complete Mediation `artifact://evemisslab/adaptive-epistemic-systems/AER-0_MVP_v0.1_Architecture_Comparison_R5_Complete_Mediation.zip`	`ACTIVE`	`REL-2026-0146`
`EXP-2026-0006` R5——完全中介與繞過抗性	`produces`	`RST-2026-0004` R5 十情境統計	`ACTIVE`	`REL-2026-0147`
`EXP-2026-0007` R6——外部信任 anchor、程序分離 writer、adapter 一致性	`extends`	`EXP-2026-0006` R5——完全中介與繞過抗性	`ACTIVE`	`REL-2026-0152`

歷史與來源歷程

Canonical URL

https://evemisslab.com/ai/experiments/EXP-2026-0006/

機器可讀

/ai/experiments/EXP-2026-0006/index.json

快照

AI-SNAPSHOT-v0.1-fe85b9694a45

來源歷程

source: EveMissLab research collection: Adaptive Epistemic Systems (真本體論13)
extracted_by: Splice (Claude Code), reading the canonical UTF-8 sources and each lab's own result reports
extracted_at: 2026-09-11
generator: tools/extract_aes/extract.py
claim_boundary: status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports