arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2610.23362cs.AIcs.CRcs.SE
收藏

监控器有效性失效:演进框架边界处的大语言模型安全证据路径

Monitor-Validity Failures: LLM Safety Evidence Paths at Evolving Framework Boundaries

Junchi Liao

AI总结:

该研究针对LLM应用中监控器有效性失效问题,提出金丝雀合约协议,在11个项目组及4个生态系统中确认18条证据路径失效,为框架演进的监控器回归测试提供依据。

摘要:

现代大语言模型(LLM)应用依赖运行时监控器,该监控器会检查工具调用、轨迹、流、检测器输出及验证器输入。这产生了接口可靠性问题:某一框架路径可能仍保持可运行状态,但与策略相关的证据却从未到达其决策点。在一个代表性案例中,正则表达式(regex)检测器返回了阳性匹配结果,但框架在做出阻止决策前就搁置了该结果。这与越狱(jailbreaks)和检测器错误不同,因为证据已被识别却与执行环节断开。我们通过金丝雀合约(canary contracts)研究这种修复边界特征:父级/固定确认单元仅在变更后的证据表面放置已知有效载荷,并记录监控器可见性以及行动边界案例的下游决策。将该协议应用于公开框架修复,我们在11个LLM或智能体安全项目组及4个实施生态系统中确认了18条证据路径失效。其中9个为已建立边界的修复,8个为新策略覆盖缺口,1个为仅边界证据案例。14个案例到达E1执行边界:7个原生行动结果、6个配置的执行边界、1个合成消费者后果。其余案例影响验证器、安全提示或可观测性通道。这些案例形成载体、适配器、权限及表面类别,表明普通应用行为可保持完整,而特定安全证据路径却会错过其决策。精确修订、确定性结果、阴性对照及冻结的前瞻性审计记录了确认规则。因此,监控器假设需要在框架演进的模式、流、工具及适配器处进行回归测试。

英文摘要:

Modern LLM applications rely on runtime monitors that inspect tool calls, traces, streams, detector outputs, and verifier inputs. This creates an interface-reliability problem: a framework path may remain operational while policy-relevant evidence never reaches its decision point. In one representative case, a regex detector returned a positive match, but the framework stranded the result before the block decision. This differs from jailbreaks and detector errors because the evidence is already recognized yet disconnected from enforcement. We study this repair-boundary signature with canary contracts: parent/fixed confirmation units that place a known payload only on the changed evidence surface and record monitor visibility together with the downstream decision for action-boundary cases. Applying the protocol to public framework repairs, we confirm 18 evidence-path failures across 11 LLM or agent safety project groups and four implementation ecosystems. Nine are established-boundary repairs, eight are new-surface policy-coverage gaps, and one is a boundary-only evidence case. Fourteen reach E1 enforcement boundaries: seven native action outcomes, six configured enforcement boundaries, and one synthetic-consumer consequence. The remaining cases affect verifier, safety-prompt, or observability channels. The cases form carrier, adapter, authority, and surface families and show how ordinary application behavior can remain intact while a safety-specific evidence path misses its decision. Exact revisions, deterministic outcomes, negative controls, and a frozen prospective audit document the confirmation rule. Monitor assumptions therefore need regression tests at the schemas, streams, tools, and adapters that frameworks evolve.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑