Swift Hydra: Self-Reinforcing Generative Framework for Anomaly Detection with Multiple Mamba Models

2025-03-09

AI Summary

To address the limited generalization capability of existing anomaly detection methods against unknown anomalies, this paper proposes a generative AI–reinforcement learning (RL) co-enhanced framework. The framework employs an RL policy network to guide a variational generative model in synthesizing diverse anomalous samples within the latent space—samples specifically designed to evade the current detector—enabling closed-loop data augmentation and iterative model refinement. Technically, it introduces a novel Mamba-MoE architecture that dynamically activates expert subnetworks based on input data complexity, thereby balancing expressive modeling capacity with inference efficiency. Evaluated on the ADBench benchmark, the method achieves an average AUC improvement of 3.2% and reduces inference latency by 27% over state-of-the-art approaches. To our knowledge, this is the first work to jointly optimize both high detection accuracy and low inference delay for unknown anomaly detection.

Technology Category

• Machine Learning: Mixture of Experts (MoE)
• Data Mining & Knowledge Management: Anomaly/Outlier Detection
• Search and Optimization: Learning to Search

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

Despite a plethora of anomaly detection models developed over the years, their ability to generalize to unseen anomalies remains an issue, particularly in critical systems. This paper aims to address this challenge by introducing Swift Hydra, a new framework for training an anomaly detection method based on generative AI and reinforcement learning (RL). Through featuring an RL policy that operates on the latent variables of a generative model, the framework synthesizes novel and diverse anomaly samples that are capable of bypassing a detection model. These generated synthetic samples are, in turn, used to augment the detection model, further improving its ability to handle challenging anomalies. Swift Hydra also incorporates Mamba models structured as a Mixture of Experts (MoE) to enable scalable adaptation of the number of Mamba experts based on data complexity, effectively capturing diverse feature distributions without increasing the model's inference time. Empirical evaluations on ADBench benchmark demonstrate that Swift Hydra outperforms other state-of-the-art anomaly detection models while maintaining a relatively short inference time. From these results, our research highlights a new and auspicious paradigm of integrating RL and generative AI for advancing anomaly detection.

Problem

• Improves generalization to unseen anomalies in critical systems.
• Introduces Swift Hydra for anomaly detection using generative AI and RL.
• Enhances detection models with synthetic anomalies and scalable Mamba models.

Innovation

• Generative AI and RL for anomaly detection
• Mamba models in Mixture of Experts structure
• Synthetic anomaly samples enhance detection model