Search papers, labs, and topics across Lattice.
This paper presents an adaptive intrusion detection system (IDS) that integrates a tabular transformer encoder with a class-balanced experience replay buffer to mitigate the effects of catastrophic forgetting in the face of evolving threat landscapes. By introducing a class-instance incremental (CII) scenario, the authors effectively demonstrate that replaying benign traffic alongside new attacks can stabilize decision boundaries, achieving high accuracy on the CICIDS2017 benchmark. However, the study also reveals significant vulnerabilities in the replay buffer, where adversarial attacks like label flipping can drastically degrade model performance, highlighting the need for robust buffer integrity measures.
A novel IDS framework achieves near-perfect accuracy while revealing critical vulnerabilities in replay buffers that can be exploited by adversarial attacks.
Network intrusion detection systems (IDS) trained on fixed traffic snapshots decay silently after deployment as threat distributions shift. Fine-tuning models on new attacks triggers catastrophic forgetting, while retraining from scratch is computationally infeasible. Replay-based continual learning counters this, but existing methods unrealistically confine benign traffic to a single early task and ignore the replay buffer as a potential attack surface. To address this, we present an adaptive IDS framework coupling a tabular transformer encoder with a class balanced experience replay buffer that replays benign traffic at every update to stabilize decision boundaries. We introduce the class-instance incremental (CII) scenario where benign flows reappear alongside new attacks as a more faithful stress test, and probe the buffer with overt label flipping and stealthy backdoor poisoning attacks. On the CICIDS2017 benchmark, our framework achieved 0.9994 accuracy under the traditional class incremental setup and 0.9989 under CII, with negligible forgetting, drastically outperforming sequential fine-tuning (0.0052), EWC (0.0324), LwF (0.0699), and iCaRL (0.8770) baselines. While injecting benign traffic into every experience proves essential for preventing forgetting, the replay buffer introduces critical vulnerabilities. Label-flipping collapses the model entirely (0.0053 accuracy at a 1% budget), and the backdoor maintains 0.97 overall accuracy while driving the attack success rate on trigger flows to 95%, evading standard monitoring. Ultimately, while a modest replay budget recovers near-joint-training performance, ensuring buffer integrity emerges as a strict operational requirement.
