PANDORA: Lightweight Adversarial Defense for Edge IoT using Uncertainty-Aware Metric Learning
Avinash Awasthi
Network and Distributed System Security (NDSS) Symposium 2026 · Day 3 · Web Security
PANDORA is a lightweight intrusion detection system (IDS) framework designed for **resource-constrained edge IoT devices** that addresses three fundamental challenges in network security monitoring: **domain shift** (adapting across different IoT environments), **concept drift** (evolving traffic patterns over time), and **concept shift** (detecting zero-day attacks). The framework combines a **Mamba backbone** with a **Mixture of Experts (MoE)** architecture to achieve linear time complexity suitable for edge deployment, while using a novel **Probabilistic Manifold Structuring and Distance (PMSD) loss function** for uncertainty-aware metric learning.
AI review
An ML-heavy IDS framework that claims 98-100% zero-day detection accuracy and 0.99 cross-domain generalization, but the presentation lacks the rigor needed to evaluate these extraordinary claims. The attack scenarios are self-generated, the zero-day detection is tested against held-out classes from the same distribution rather than truly novel attacks, and the Q&A revealed legitimate concerns about dataset composition that went unanswered.