FIRCE: A Framework for Intrusion Response and Conformal Evaluation

TL;DR

FIRCE is a framework that enhances intrusion detection systems with conformal evaluation and adaptive mechanisms to detect and respond to concept drift in real-time environments.

Contribution

It introduces a novel conformal evaluation strategy and adaptive chunking mechanism for improved drift detection and response in intrusion detection systems.

Findings

FIRCE effectively detects distributional shifts in IoT network traffic.

The adaptive chunking improves drift responsiveness without high computational costs.

Benchmarking shows FIRCE's robustness across multiple datasets.

Abstract

Machine learning-based intrusion detection systems deployed in real-world environments frequently suffer from model degradation due to concept drift, where changes in traffic patterns invalidate training assumptions. To address this, we present FIRCE, a Framework for Intrusion Response and Conformal Evaluation that augments supervised IDS classifiers with conformal evaluation-based uncertainty quantification and drift detection. FIRCE supports four conformal evaluation strategies: Inductive, Cross, Approximate Transductive, and our proposed Approximate Cross-Conformal Evaluator, which achieves robust performance with minimal calibration overhead. FIRCE also introduces an adaptive chunking mechanism that dynamically adjusts evaluation granularity in response to stream volatility, improving drift responsiveness while preserving computational efficiency. Using a custom IoT testbed of 10 commercial devices and time-series network captures under simulated attack and drift conditions, we demonstrate FIRCE's ability to detect distributional shifts and trigger model retraining. We additionally benchmark FIRCE on the CICIDS2018 and UNSW-NB15 datasets to validate its generalizability. Experimental results show that conformal evaluation-based drift detection, combined with adaptive chunking, enables an efficient and robust response to evolving threats.