---
title: "Uncertainty-Guided Cross-Modal Alignment for Diffusion-Based IoT Intrusion Detection"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2610.39117v1"
permalink: "https://feed.astralor.com/items/itm_7bded90f40c0fdaf3e44ee7c"
published: "2026-10-29T01:01:47.000Z"
score: 57
channel: "ai"
tags: ["安全","RAG","多模态","Uncertainty-Guided Cross-Modal Alignment","Diffusion-Based IoT Intrusion","Detection Diffusion","Diffusion","VAE"]
---

# Uncertainty-Guided Cross-Modal Alignment for Diffusion-Based IoT Intrusion Detection

## 速览

Diffusion models evolve noisy states toward a learned data distribution, so their sampling behavior depends on the geometry of the representation in which denoising occurs. This dependence is especially important for mu…

## 关键点

- Diffusion models evolve noisy states toward a learned data distribution, so their sampling behavior depends on the geometry of the representation in which denoising occurs.
- This dependence is especially important for multimodal data: independently trained encoders can map synchronized views to incompatible latent regions, while uniform alignment can let an uncertain view distort the shared…
- To address this gap, we introduce a novel reliability-guided alignment rule that uses normalized VAE posterior variance to control directional cross-modal influence before diffusion training.

## 全文

Diffusion models evolve noisy states toward a learned data distribution, so their sampling behavior depends on the geometry of the representation in which denoising occurs. This dependence is especially important for multimodal data: independently trained encoders can map synchronized views to incompatible latent regions, while uniform alignment can let an uncertain view distort the shared geometry. To address this gap, we introduce a novel reliability-guided alignment rule that uses normalized VAE posterior variance to control directional cross-modal influence before diffusion training. We study this issue in minority-attack generation for imbalanced Internet-of-Things intrusion detection. Tabular flow attributes, a DeepInsight image, and a packet sequence are encoded by modality-specific variational autoencoders. Per-modality normalized VAE posterior variances provide bounded, sample-specific weighting signals in an asymmetric stop-gradient alignment objective. We use these quantities as heuristic encoder-derived reliability proxies rather than calibrated probabilistic uncertainties. The full modality-specific latent means obtained after alignment fine-tuning are standardized and modeled jointly by a class-conditional EDM; a second-order sampler then generates paired attack-conditioned latent blocks for the three decoders. In controlled experiments on TON-IoT, uncertainty-aware alignment obtains the highest mean precision, recall, density, and coverage among three diffusion variants. Augmenting only the training split yields ROC-AUC 0.9515, PR-AUC 0.8954, balanced accuracy 0.8395, and attack-class F1 0.7940 on an untouched real test set. Among the two variants with matched alignment fine-tuning, posterior-variance-based weighting improves both tabular generative fidelity and downstream detection relative to uniform weighting.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_7bded90f40c0fdaf3e44ee7c