Cross-Domain Generalization Failure in Lightweight Intrusion Detection Models for IIoT Networks

• 类型：arxiv
• 标识：2607.00553
• 链接：https://arxiv.org/abs/2607.00553
• 主分类：evaluation
• 形态：application
• 被引：1
• 被引来源：Semantic Scholar
• S2被引：1
• OpenAlex被引：0
• 影响力被引：1
• TLDR：Deployment readiness should be assessed using cross-network evaluation under realistic class distributions, rather than within-domain accuracy alone, to suggest deployment readiness should be assessed using cross-network evaluation under realistic class distributions, rather than within-domain accuracy alone.
• OpenAlex ID：W7167033814
• OpenAlex DOI：10.48550/arxiv.2607.00553
• DOI：10.48550/arxiv.2607.00553
• DOI来源：OpenAlex
• 开放获取：green
• 开放获取链接：https://doi.org/10.48550/arxiv.2607.00553
• OpenAlex更新：2026-07-19
• 副分类：engineering
• 待LLM分类：否
• 标题中文：面向 IIoT 网络的轻量级入侵检测模型的跨域泛化失效
• TLDR中文：应在真实类别分布下使用跨网络评估来判断部署就绪度，而非仅依赖域内准确率。
• 来源文件：
• /inbox/tom/_candidates/2026-07-02-agent-rag-longcontext-candidates.json
• [S2 enrich]
• [OpenAlex backfill]