arXiv subjects

Yongzhe Xu

Publications and source records attributed to Yongzhe Xu.

3 recordsLinked to original sources

arXiv2025

ASINT: Learning AS-to-Organization Mapping from Internet Metadata

Accurate AS-to-organization mapping underpins Internet measurement and security, yet registries are fragmented, PeeringDB is narrow, and routing views reflect connectivity rather than ownership. We take a pragmatic step: ASINT integrates curated web evidence with retrieval-guided LLM techniques and strict, evidence-cited validation to infer two relations (aliases and directed parent-child) and then revalidates them conservatively. To keep the dataset sustainable, we operate a public dashboard and API where operators can inspect per-ASN evidence and submit feedback that seeds refreshes. At scale, ASINT maps 112,172 ASNs into 82,840 organization families and, on overlapping AS sets, yields fewer, larger families with 21-24% more multi-AS groups than prior datasets (i.e., CAIDA AS2Org [11], AS2ORG+ [4], AS-Sibling [10], and Borges [28]). Quality is high in practice: ASINT achieves a precision of 0.9608, a recall of 0.9915 and an accuracy of 0.9752 under manual validation. Public deployment further drew operator-submitted reports for 595 ASNs across 106 organizations, with only 6 errors (99.0% observed clustering accuracy), with feedback coming from network operators across all RIR regions. Better organization context improves downstream analyses: +27.5% intra-organization RPKI misconfiguration detections, -9.4% benign hijack alerts, and -5.9% corrections to cases mislabeled as IP leasing. We release code, datasets, and the operator platform with APIs; given persistent ambiguity in organizational names and the continual evolution of corporate structures, an operator-in-the-loop process is essential; the platform records per ASN feedback with provenance and incorporates it into periodic refreshes and retraining. The methodology is model-agnostic and stands to improve further as base LLMs advance.

cs.NI↗

arXiv2024

Modeling Dual-Exposure Quad-Bayer Patterns for Joint Denoising and Deblurring

Image degradation caused by noise and blur remains a persistent challenge in imaging systems, stemming from limitations in both hardware and methodology. Single-image solutions face an inherent tradeoff between noise reduction and motion blur. While short exposures can capture clear motion, they suffer from noise amplification. Long exposures reduce noise but introduce blur. Learning-based single-image enhancers tend to be over-smooth due to the limited information. Multi-image solutions using burst mode avoid this tradeoff by capturing more spatial-temporal information but often struggle with misalignment from camera/scene motion. To address these limitations, we propose a physical-model-based image restoration approach leveraging a novel dual-exposure Quad-Bayer pattern sensor. By capturing pairs of short and long exposures at the same starting point but with varying durations, this method integrates complementary noise-blur information within a single image. We further introduce a Quad-Bayer synthesis method (B2QB) to simulate sensor data from Bayer patterns to facilitate training. Based on this dual-exposure sensor model, we design a hierarchical convolutional neural network called QRNet to recover high-quality RGB images. The network incorporates input enhancement blocks and multi-level feature extraction to improve restoration quality. Experiments demonstrate superior performance over state-of-the-art deblurring and denoising methods on both synthetic and real-world datasets. The code, model, and datasets are publicly available at https://github.com/zhaoyuzhi/QRNet.

eess.IV↗

arXiv2022

D2HNet: Joint Denoising and Deblurring with Hierarchical Network for Robust Night Image Restoration

Night imaging with modern smartphone cameras is troublesome due to low photon count and unavoidable noise in the imaging system. Directly adjusting exposure time and ISO ratings cannot obtain sharp and noise-free images at the same time in low-light conditions. Though many methods have been proposed to enhance noisy or blurry night images, their performances on real-world night photos are still unsatisfactory due to two main reasons: 1) Limited information in a single image and 2) Domain gap between synthetic training images and real-world photos (e.g., differences in blur area and resolution). To exploit the information from successive long- and short-exposure images, we propose a learning-based pipeline to fuse them. A D2HNet framework is developed to recover a high-quality image by deblurring and enhancing a long-exposure image under the guidance of a short-exposure image. To shrink the domain gap, we leverage a two-phase DeblurNet-EnhanceNet architecture, which performs accurate blur removal on a fixed low resolution so that it is able to handle large ranges of blur in different resolution inputs. In addition, we synthesize a D2-Dataset from HD videos and experiment on it. The results on the validation set and real photos demonstrate our methods achieve better visual quality and state-of-the-art quantitative scores. The D2HNet codes and D2-Dataset can be found at https://github.com/zhaoyuzhi/D2HNet.

cs.CV↗