Necessity of a Dual-Engine Paradigm: Resolving the Robustness-Adaptability Trade-off in Anomaly Detection

计算机科学 异常检测 人工智能 模式识别(心理学) 目标检测 计算机视觉 特征提取 雷达成像 雷达跟踪器 异常(物理) 特征(语言学) 合成孔径雷达 图像处理 图像分割 遥感
作者
Jian De Zheng,Jiangli Duan,Lin Li,Shengye Wang,Cuijuan Zhang,Haichao Sun,Huyong Yan
出处
期刊:IEEE Transactions on Pattern Analysis and Machine Intelligence [IEEE Computer Society]
卷期号:PP: 1-14
标识
DOI:10.1109/tpami.2026.3733282
摘要

The trade-off between model-driven robustness and data-driven adaptability is a fundamental challenge in machine learning, particularly for anomaly detection in non-stationary environments. Here, we prove mathematically that no single-engine architecture can overcome a detection completeness lower bound- any monolithic model must sacrifice either robustness or adaptability (Theorem 7). This impossibility necessitates a paradigm shift: instead of seeking a single optimal model, we must architecturally integrate two complementary information sources. To realize this principle, we propose the Dual-Engine Anomaly Detection Framework (dEADF), combining a Gaussian Orthogonal Ensemble (GOE) macro-statistical engine with a Multi-granularity Liquid Neural Network (MLNN) micro-dynamic engine. The GOE engine provides a theoretically grounded neutral reference manifold that preserves normal geometry and amplifies anomalies (Theorems 1-4). The MLNN engine captures adaptive, data-driven temporal patterns. Their integration is stabilized by GOE-guided regularization, which convexifies the loss landscape and tightens generalization bounds (Theorem 6 and Corollary 6.1). Feature-space complementarity (Theorem 5) and an optimal dimension principle (Theorem 8) further ensure that the two engines operate synergistically, while universality results (Theorem 9) delineate the framework's operational boundary under heavy-tailed distributions. We validate dEADF on three benchmarks-financial transactions, credit card fraud, and network intrusion-including a proprietary dataset with 1.42 million unlabeled transactions for deployment analysis. Without domain-specific feature engineering, dEADF achieves state-of-the-art performance across multiple metrics against 13 existing methods. This work does not propose an incremental model; rather, it identifies a mathematical necessity and provides the first constructive proof-of-concept for anomaly detection systems that are both theoretically grounded and adaptively powerful.
最长约 10秒,即可获得该文献文件

科研通智能强力驱动
Strongly Powered by AbleSci AI
科研通是完全免费的文献互助平台,具备全网最快的应助速度,最高的求助完成率。 对每一个文献求助,科研通都将尽心尽力,给求助人一个满意的交代。
实时播报
刚刚
刚刚
LongH2完成签到,获得积分10
刚刚
淡然远山发布了新的文献求助10
1秒前
1秒前
YTJ完成签到,获得积分10
1秒前
鲤鱼天奇发布了新的文献求助10
1秒前
2秒前
852的应助被开心德地采纳,获得10
2秒前
TYM发布了新的文献求助10
3秒前
Sunday发布了新的文献求助30
4秒前
4秒前
lwr发布了新的文献求助10
4秒前
fighter完成签到,获得积分10
4秒前
Hello的应助被lvy采纳,获得10
4秒前
Orange的应助被lvy采纳,获得10
4秒前
共享精神的应助被外向新梅采纳,获得10
5秒前
科研通AI6.2的应助被原神大王采纳,获得10
5秒前
6秒前
shenkekeshen的应助被dididi采纳,获得10
6秒前
搜集达人的应助被开心德地采纳,获得10
6秒前
8秒前
TGU发布了新的文献求助10
9秒前
Hello的应助被开心德地采纳,获得10
9秒前
CipherSage的应助被山野的雾采纳,获得10
12秒前
小二郎的应助被开心德地采纳,获得30
13秒前
kelly发布了新的文献求助10
13秒前
超级无敌发布了新的文献求助10
13秒前
14秒前
搜集达人的应助被开心德地采纳,获得10
16秒前
17秒前
科研通AI65的应助被tianxings采纳,获得10
17秒前
小古发布了新的文献求助10
18秒前
18秒前
kelly完成签到,获得积分10
19秒前
砍柴少年发布了新的文献求助10
19秒前
CipherSage的应助被liu采纳,获得10
19秒前
鲤鱼天奇完成签到,获得积分20
19秒前
molihuakai的应助被Yxianzi采纳,获得10
19秒前
ket的应助被大兔米菲采纳,获得10
19秒前
高分求助中
(应助此贴封号)【重要!!请各用户(尤其是新用户)详细阅读】【科研通的精品贴汇总】 10000
拉伸高分子熔体中缠结行为的模拟和小角中子散射研究 1700
The World Atlas of Wine 9th edition 1000
Sex, Aging, and Death in a Medieval Medical Compendium: Trinity College Cambridge MS R.14.52, Its Texts, Language, and Scribe 500
高分子基功能界面水蒸发材料与应用研究 500
外场增强的水汽发电研究 500
基于结构调控的功能化水诱导发电材料与器件研究 500
热门求助领域 (近24小时)
化学 材料科学 医学 生物 纳米技术 计算机科学 工程类 有机化学 化学工程 生物化学 物理 复合材料 内科学 催化作用 光电子学 人工智能 细胞生物学 无机化学 物理化学 数学
热门帖子
关注 科研通微信公众号,转发送积分 8189302
求助须知:如何正确求助?哪些是违规求助? 9576666
关于积分的说明 21849295
捐赠科研通 7787245
什么是DOI,文献DOI怎么找? 3435521
关于科研通互助平台的介绍 2559748
邀请新用户注册赠送积分活动 2482509