ScenarioForge:自动生成并实测验证网络攻防演练场景
ScenarioForge: Resource-Grounded Generation and Execution Validation of Cyber Exercises
搞靶场或 CTF 出题的朋友可以看看这篇:ScenarioForge 把需求直接变成能在 CORE 里跑起来的演练场景,226 个场景全部实测通过。对照实验显示,直接让 Qwen3.8 或 GPT5.6 裸写拓扑做不到全成功,套上它的结构化脚手架才能到 100%。做安全训练平台或红队工具链的团队值得跟进复现。
arXiv 论文提出 ScenarioForge,将高层需求转化为可部署的网络攻防演练场景,在 CORE(Common Open Research Emulator)中实例化并验证。配套的 Execution Dataset 包含 226 个真实落地场景,覆盖 294 个 Vulhub 镜像和 85 个自建挑战资源生成器,全部通过构建、预览、排序、部署、严格运行时验证和活体产物检查,共 867 个可逐项验证的挑战步骤,其中 457 个基于真实漏洞、410 个基于生成资源。
在 50 条提示词的对照组基准中,ScenarioForge+Qwen3.8 与 ScenarioForge+GPT5.6 均达到 50/50 拓扑构建成功率和 160/160 意图字段匹配;直接用前沿模型生成在叠加完整脚手架(结构、词表、策略、容器镜像指引)后仅达 41/50 构建和 147/160 字段,且未包含下游资源生成、flag 依赖排序、部署与活体验证环节。
对网络靶场和 CTF 内容作者而言,该工作把基础设施编排、漏洞服务、攻击路径与成功条件校验流水线化,产出可直接复现的训练与评测环境,显著降低逐场景手工搭建的成本。
ScenarioForge: Resource-Grounded Generation and Execution Validation of Cyber Exercises
Cyber-range and capture-the-flag scenario construction remains labor-intensive because authors must coordinate infrastructure, vulnerable services, attack paths, artifacts, and success conditions. LLMs can propose detailed exercises, but plausible descriptions do not guarantee deployable software or verifiable objectives. We present ScenarioForge, which turns high-level requirements into resource-grounded topologies, services, traffic, segmentation, and challenge chains, then instantiates and validates them in the Common Open Research Emulator (CORE). The ScenarioForge Execution Dataset contains 226 materialized scenarios covering 294 Vulhub images and all 85 custom-built challenge-resource generators developed with our AI-assisted scaffolding. All 226 passed construction, preview, sequencing, deployment, strict runtime validation, and live artifact checks; their 867 steps, each an individually verifiable challenge objective, comprise 457 vulnerability-backed and 410 generated-resource-backed instances. In a separate 50-prompt matched benchmark, ScenarioForge+Qwen3.8 and ScenarioForge+GPT5.6 each achieved 50/50 (100%) topology/build success and 160/160 intent fields; direct frontier generation reached 41/50 builds and 147/160 fields only with the full cumulative scaffold: structure, vocabulary, policy, and container-image guidance. The test still omitted ScenarioForge's downstream challenge-resource generation, dependency/flag sequencing, deployment, and live validation. The artifacts support operationally rich, reproducible exercises for training and evaluation.
本条情报归属 AITOP「论文」核心追踪栏目。在跨区域产业观察坐标中,该动态直接关联「AI 开发者工具链、Coding Agent 与工程化实践」研究主线,反映出当前技术演进与商业落地的最新风向。涉及核心实体与技术议题包括:ScenarioForge、Qwen3.8、GPT5.6、网络靶场,读者可通过下方标签进入对应专题页查阅历史脉络与关联对比。
信源核验说明:本文原始线索采编自「arXiv cs.AI」(@Jaime C. Acosta, Anantaa Kotal, Aritran Piplai),经 AITOP 多维评分管线结构化提炼。