Towards Principled Continual Anomaly Detection: A Systematic Framework and Benchmark Scenarios

AI 中文解读

别眨眼，AI异常检测领域迎来一次“标准化”大升级！——最新研究提出一套系统框架，专治“持续异常检测”中任务乱划分、效果难复现的顽疾，让AI在追踪新威胁时不再“学了就忘”。过去，机器要一边学习新的数据模式（比如新型网络攻击），一边记住旧有的异常规则，这个过程叫“持续异常检测”。但研究人员发现，如果测试时把数据任务切分得随意、重复或无意义，就会导致AI表现忽好忽坏，很难判断它到底有没有在真正“持续学习”。这篇论文就像给混乱的实验加上了“流程规范”：它设计了一套自动方法，能从现有数据集中找出真正值得学的新任务，筛掉无用或太简单的，并按难度排序，让AI循序渐“学”。最终，三个大型网络安全数据集、五个标准化测试场景就出炉了。对普通人来说，这项技术最大的影响藏在幕后。当你使用在线银行、企业内网或云服务时，系统背后的异常检测模型会不断适应新型欺诈或黑客手段。有了这套框架，安全工程师就能更科学地评估模型的真实持续学习能力，减少误报和漏报，你的数据和账户也就更稳更安全了。

arXiv:2607.18289v1 Announce Type: new Abstract: Continual anomaly detection (CAD) studies how models can adapt to evolving data distributions while retaining performance on previously observed regimes. CAD benchmarks, however, depend critically on how tasks are defined, filtered, ordered, and validated. In tabular domains, task boundaries are rarely given, and arbitrary splits can create unlearnable, redundant, or overly transferable tasks that obscure genuine continual-learning behavior. To this end, we introduce a systematic framework for reproducible benchmark scenario design from existing tabular anomaly-detection datasets. The framework discovers candidate tasks, filters unsuitable tasks, and derives principled orderings that expose diverse dynamics. The framework allows us to deliver five benchmark-ready scenarios from three large-scale cybersecurity anomaly detection datasets, yielding both single-dataset and multi-dataset CAD settings.