DeepString: Alibaba's Anti‑Fraud Platform Using Large Models for Real‑Time Traffic Detection

Alibaba's anti-fraud platform DeepString uses large unsupervised models to detect abnormal traffic in real time across multiple advertising products, combining a foundation model for event mining, anomaly measurement, and an alignment model for online filtering, reducing reliance on manual labeling and domain expertise.

algorithm frameworkanti-fraudlarge models

0 likes · 19 min read

DeepString: Alibaba's Anti‑Fraud Platform Using Large Models for Real‑Time Traffic Detection

Meituan Technology Team

Mar 2, 2023 · Artificial Intelligence

Technical Innovations in YOLOv6 3.0 for Real‑Time Object Detection

YOLOv6 3.0 raises real‑time object detection performance to a new peak with 57.2% AP and 29 FPS on a T4 GPU, surpassing YOLOv7‑E6E, and introduces RepBi‑PAN Neck, Anchor‑Aided Training, and Decoupled Location Distillation to boost accuracy and efficiency.

Anchor-Aided TrainingDecoupled Location DistillationRepBi-PAN

0 likes · 13 min read

Technical Innovations in YOLOv6 3.0 for Real‑Time Object Detection

转转QA

Apr 1, 2022 · Information Security

Design and Implementation of the Cleaner Anti‑Crawler System for Real‑Time Bot Detection

This article presents a comprehensive design of the Cleaner anti‑crawler system, detailing its background, current challenges, related research, system architecture—including a Flink‑based data processing center, a strategy‑driven ban center, and a lightweight ban store—and evaluates its effectiveness in real‑time bot mitigation.

Backend Securityanti‑crawlerrate limiting

0 likes · 17 min read

Design and Implementation of the Cleaner Anti‑Crawler System for Real‑Time Bot Detection

Baidu Intelligent Testing

Sep 14, 2021 · Information Security

Community Encoding Based Detection of Black and Gray Market Attacks Using Graph Embedding

This article presents a community‑encoding approach that leverages large‑scale graph‑embedding (GraphSAGE) and asynchronous near‑real‑time engineering to identify and measure unknown black‑gray market attacks with higher accuracy and flexibility than traditional graph‑mining methods.

GraphSAGEUnsupervised Learningblack‑gray market

0 likes · 15 min read

Community Encoding Based Detection of Black and Gray Market Attacks Using Graph Embedding

JD Retail Technology

Sep 2, 2019 · Operations

How a Real‑Time H5 Monitoring Platform Solves E‑Commerce Activity Issues

Facing frequent user complaints about broken, slow, or misleading H5 activity pages, JD’s massive e‑commerce operations categorize issues into four types and deploy the Woodpecker platform—a scalable, real‑time monitoring and analysis system that pre‑detects configuration errors, server faults, development bugs, and minor UX flaws, while offering extensible, configurable alerts and historical scans.

AIH5 monitoringOperations

0 likes · 15 min read

How a Real‑Time H5 Monitoring Platform Solves E‑Commerce Activity Issues