QCL-IDS: Quantum Continual Learning for Intrusion Detection with Fidelity-Anchored Stability and Generative Replay

TL;DR

QCL-IDS introduces a quantum-based continual learning framework for intrusion detection that maintains detection accuracy over time while respecting operational constraints and privacy, using fidelity-anchored stability and generative replay.

Contribution

It presents QCL-IDS, a novel quantum-centric continual learning approach with fidelity-based stability and privacy-preserving generative replay for intrusion detection.

Findings

Achieves high Attack-F1 scores (~0.94) on UNSW-NB15 and CICIDS2017 datasets.

Maintains minimal forgetting (around 0.005-0.004) during continual learning.

Outperforms sequential fine-tuning in retention and adaptation trade-offs.

Abstract

Continual intrusion detection must absorb newly emerging attack stages while retaining legacy detection capability under strict operational constraints, including bounded compute and qubit budgets and privacy rules that preclude long-term storage of raw telemetry. We propose QCL-IDS, a quantum-centric continual-learning framework that co-designs stability and privacy-governed rehearsal for NISQ-era pipelines. Its core component, Q-FISH (Quantum Fisher Anchors), enforces retention using a compact anchor coreset through (i) sensitivity-weighted parameter constraints and (ii) a fidelity-based functional anchoring term that directly limits decision drift on representative historical traffic. To regain plasticity without retaining sensitive flows, QCL-IDS further introduces privacy-preserved quantum generative replay (QGR) via frozen, task-conditioned generator snapshots that synthesize bounded rehearsal samples. Across a three-stage attack stream on UNSW-NB15 and CICIDS2017, QCL-IDS consistently attains the best retention-adaptation trade-off: the gradient-anchor configuration achieves mean Attack-F1 = 0.941 with forgetting = 0.005 on UNSW-NB15 and mean Attack-F1 = 0.944 with forgetting = 0.004 on CICIDS2017, versus 0.800/0.138 and 0.803/0.128 for sequential fine-tuning, respectively.