停下的苍蝇：蘑菇体启发的习惯化作为自主渗透测试的无奖励调度先验
The Fly That Stopped: Mushroom-Body-Inspired Habituation as a Reward-Free Scheduling Prior for Autonomous Penetration Testing
浏览论文内容
中文总结 AI 辅助
针对自主渗透测试中重复行动浪费预算的问题，提出受果蝇蘑菇体启发的无奖励调度器，通过习惯化计数器降低重复动作比率，实验验证其有效性。
中文摘要 AI 辅助
自主安全测试代理在固定的行动预算中，可能会花费大量时间重复之前选择的工具。我们评估了一种受果蝇蘑菇体新奇处理启发的无奖励调度器。该调度器将稀疏状态编码与基于结构化URL类别和工具族的衰减习惯化计数器相结合。计数器惩罚重复的干净或错误结果，而不通过标量奖励更新权重。四个匹配的战役暴露了奖励核算错误和工具失败循环，从而激发了这一设计；奖励驱动的组件在测试的主要结果上并未优于无奖励的蘑菇体条件。一项预注册的试点和两个确认阶段随后评估了重复的（工具，URL）选择。在第二个确认阶段中，在两次错误密集的慢速XSS排除后，10个筛选的实验室目标中有8个保持可测量。习惯化启用的调度器在所有6个非平局目标对中降低了重复动作比率（精确单侧p=0.015625），其中有两个平局；最大减少是在60步预算内从51步重复降至18步。这是完整调度器在可测量的预算保持群体上的证据，而非孤立的习惯化消融或漏洞发现增益。一项在13,498个神经元的MaleCNS衍生电路（501,267个突触边，权重至少为5）上的补充研究发现，在固定读出下，五种测试的局部可塑性方法没有产生动作选择性；读出可塑性在合成任务中产生了有条件的积极结果，但未建立生物拓扑优势。我们报告了群体界限、剩余的输入完整性依赖，以及一个内部AI辅助审查协议，连同结果一起。
英文摘要
Autonomous security-testing agents can spend much of a fixed action budget repeating earlier tool selections. We evaluate a reward-free scheduler inspired by mushroom-body novelty processing in Drosophila. It combines sparse state encoding with decaying habituation counters over structural URL classes and tool families. The counters penalize repeated clean or error outcomes without updating weights from scalar reward. Four matched campaigns motivated this design by exposing reward-accounting errors and tool-failure loops; reward-driven components did not improve the tested primary outcomes over the reward-free MB condition. A pre-registered pilot and two confirmatory stages then evaluated repeated (tool, URL) selections. In the second confirmatory stage, 8 of 10 screened lab targets remained measurable after two error-heavy slow-XSS exclusions. The habituation-enabled scheduler lowered duplicate-action ratios in all 6 non-tied target pairs (exact one-sided p=0.015625), with two ties; the largest reduction was 51 to 18 duplicate steps within a 60-step budget. This is evidence for the complete scheduler on the measurable budget-hold population, not an isolated habituation ablation or a vulnerability-discovery gain. A complementary study on a 13,498-neuron MaleCNS-derived circuit (501,267 synaptic edges with weight at least 5) found no action selectivity from the five tested local-plasticity approaches under a fixed readout; readout plasticity produced qualified positive results in synthetic tasks without establishing a biological-topology advantage. We report the population bounds, remaining input-integrity dependencies, and an internal AI-assisted review protocol alongside the results.
发表机构
- Independent Researcher
机构由 AI 辅助整理，请以论文原文为准。
