Tagged articles
risk detection
33 articles · Page 1 of 1
This article explains how LoongSuite-Pilot collects and structures coding agent execution records into unified event timelines, and how AgentLoop analyzes these records against task context to detect risks like prompt injection and unauthorized file deletions, enabling investigators to trace risky operations back to specific model-tool interactions.
AI safetyAgentLoopLoongSuite Pilot
0 likes · 18 min read

MedGuard, an LLM‑based gatekeeper co‑developed by Ant Group’s AI Safety Lab and Xiamen University, inserts medical fact‑checking into online consultations, extracts atomic claims, uses uncertainty‑driven evidence retrieval, and outperforms baselines while earning high clinician approval for safety and usability.
Clinical SafetyFact CheckingLLM
0 likes · 13 min read

The article presents an AI‑driven cross‑domain fund element knowledge graph that assembles runtime call‑chains, SQL templates and field registrations into trusted facts, uses multi‑agent collaboration to trace field transformations across repositories, and delivers structured risk analysis, impact‑scope queries, and automated loss‑prevention recommendations for AliExpress’s financial operations.
AIcross-domain analysisfield lineage
0 likes · 26 min read

The article explains how the open‑source CheckCC utility analyzes a full set of environment signals—IP, timezone, language, browser fingerprint, DNS, WebRTC, and container—to reveal profile conflicts that can cause Claude AI accounts to be blocked, and discusses related AI security concerns.
AI securityCheckCCClaude
0 likes · 7 min read

The article details how a transaction platform replaced fragile manual reviews and static rule engines with a data‑flywheel, model‑distillation, and a multi‑agent AI system—automating labeling, dual‑modality risk detection, and anti‑corrosion mechanisms—to achieve a 99.96% reduction in annual financial loss.
AIautomated labelingloss prevention
0 likes · 10 min read

The article presents a Flink‑Fluss‑LLM architecture that captures full‑link agent events via a non‑intrusive hook, combines semantic AI inference with deterministic CEP rules, and delivers millisecond‑level alerts for malicious user detection, tool result poisoning, and chain‑attack risk mitigation.
AI FunctionAgent SecurityFlink
0 likes · 41 min read

The article explains how a natural‑language‑driven AI platform, with pre‑configured agents and parameterized calls, can replace a complex 150‑line SKU‑combination risk‑checking algorithm in e‑commerce, dramatically improving readability, maintainability, development speed, and business value while reducing cost and response time.
AIMCPe-commerce
0 likes · 17 min read

This article details the design and deployment of a multi‑layer LLM system that automatically reads massive creator group chats, extracts structured insights, mitigates hallucinations with dual‑model verification, uses few‑shot prompting for stable output, and delivers real‑time risk alerts and operational reports.
AI operationsFew-Shot LearningLLM
0 likes · 14 min read


JD TechSep 18, 2025 · Artificial Intelligence
The article recounts how a risk‑control algorithm engineer progressively refined a generic large language model through four stages of prompt engineering—role‑playing, business knowledge injection, deeper analysis, and a double‑hypothesis decision framework—to transform it into a precise e‑commerce fraud detection expert.
AILLMe-commerce
0 likes · 12 min read

The article recounts how a risk‑control algorithm engineer progressively refined a generic large language model through four stages of prompt engineering—defining roles, dimensions, structured I/O, business rules, behavior fingerprints, and a dual‑hypothesis decision framework—to transform it into a precise e‑commerce fraud detection expert.
AIAlgorithmLLM
0 likes · 10 min read

The article recounts how a risk‑control algorithm engineer transformed a generic large language model into a specialized e‑commerce fraud detector by iteratively designing prompts, injecting business rules, structuring I/O, and introducing a dual‑hypothesis decision framework to achieve accurate, automated risk analysis.
LLMartificial intelligencemachine learning
0 likes · 11 min read

This article explores how black‑market cheating in marketing campaigns and e‑commerce is detected using graph‑based techniques such as same‑person mining, label propagation, Fraudar, and GCN models, and discusses future directions like multimodal data fusion and real‑time dynamic graph computation.
Anti-FraudFraudarGCN
0 likes · 18 min read


AntTechMay 12, 2025 · Industry Insights
An award‑winning joint project by Shanghai Jiao Tong University and Ant Group unveils a multimodal foundation model and advanced detection techniques that dramatically improve AI‑driven content risk governance across massive online services.
AIAnt Groupcontent safety
0 likes · 3 min read


AntTechMay 6, 2025 · Information Security
This article presents a comprehensive overview of the security challenges in HarmonyOS native ArkTS applications and describes the design and implementation of a specialized static analysis framework—including source extraction, data‑flow and inter‑function analysis, knowledge‑graph construction, and risk inference engine—while also outlining integration into development pipelines and future research directions.
ArkTScode analysisknowledge graph
0 likes · 17 min read

This article details Alibaba's security team's comprehensive approach to detecting ArkTS code vulnerabilities in HarmonyOS apps, covering architectural design, static analysis techniques, knowledge‑graph modeling, CI/CD integration, and future AI‑driven enhancements.
ArkTSHarmonyOSSecurity
0 likes · 17 min read

This article explains how AI technologies are applied to freight safety, detailing the challenges of traditional controls, the architecture of a real‑time AI safety system, data processing, risk detection, tiered interventions, and the resulting improvements in accuracy and operational efficiency.
AIComputer Visiondata privacy
0 likes · 7 min read


AntTechApr 2, 2024 · Information Security
This article outlines Ant Group's Web3 multi‑dimensional intelligent anti‑money‑laundering platform, detailing common cryptocurrency risk types, regulatory compliance challenges, and the platform's real‑time monitoring, contract scanning, and graph‑based risk tagging capabilities for proactive detection and rapid response.
Blockchain SecurityWeb3anti-money laundering
0 likes · 9 min read

The article details Bilibili's comprehensive anti‑crawling solution, covering the problem background, a two‑layer detection framework integrated with APIGW and GAIA, risk perception, strategy iteration, verification mechanisms, quantitative results, and future improvement directions, all illustrated with concrete examples and performance numbers.
API SecurityBilibiliGateway
0 likes · 23 min read

This article details Bilibili's comprehensive anti‑crawling system, covering the background of API abuse, the data‑flow framework, risk perception, strategy iteration, verification mechanisms, gateway signing design, and the measurable impact on normal and special‑case interfaces.
BilibiliGatewayVerification
0 likes · 19 min read

This article examines the profit motives and characteristics of black‑market activities targeting the Vivo game platform, outlines common cheating methods such as volume‑boosting, network attacks, and account theft, and presents Vivo's multi‑layered anti‑cheat framework with real‑world case studies.
Game SecurityGaming Industryanti-cheat
0 likes · 14 min read

The article presents a comprehensive overview of how graph algorithms are applied in Alibaba's e‑commerce risk control system, detailing six sections that include risk scenario introductions, interaction and product content risk methods, dynamic heterogeneous graph practices, a large‑scale competition, and future research directions.
Dynamic GraphGraph AlgorithmsGraph Neural Networks
0 likes · 18 min read

This article outlines the background, risk scenarios, and technical design of Ziroom's risk control platform, describing how decision‑engine calculations, data‑driven feature extraction, and rule‑based strategies are used to identify and mitigate fraudulent account activities and reduce bad‑debt losses.
Risk Controldata analysisdecision engine
0 likes · 7 min read

The article explains how ad traffic fraud—ranging from simulated impressions to click farms—can be combated using a four‑layer risk‑control system that leverages unsupervised (DBSCAN, Isolation Forest) and supervised (Logistic Regression, Random Forest) algorithms, detailing data pipelines, model training, monitoring, and real‑world case studies.
Ad FraudAdvertisingAnti-Fraud
0 likes · 15 min read

This article explains how AI technologies enable end‑to‑end freight safety monitoring, from pre‑trip and in‑trip risk identification to targeted interventions and governance, addressing challenges such as long‑tail data, small‑sample learning, fine‑grained classification, and multi‑level filtering.
AIdeep learningfreight safety
0 likes · 12 min read

This presentation details how Huya leverages computer‑vision algorithms to detect and mitigate risky content such as political, pornographic, and violent material in live‑streaming and short‑video platforms, describing system architecture, labeling strategies, algorithmic pipelines, real‑time moderation techniques, and future research directions.
AI safetyComputer VisionContent moderation
0 likes · 11 min read

This article explains the fundamentals of device fingerprinting, its technical implementation, SDK composition, privacy compliance requirements, and how it is applied in risk control scenarios such as gaming and fraud detection.
AndroidDevice FingerprintingSDK
0 likes · 10 min read

This article details Alibaba Mama's traffic quality team's comprehensive approach to identifying and curbing advertiser arbitrage through crowdsourced traffic detection, statistical baselines, behavior‑sequence modeling, graph mining, RPM perception, insight platforms, and downstream remediation, highlighting challenges and future directions.
Ad Fraudarbitrageindustry insights
0 likes · 19 min read

Lin Yuansheng, JD’s first post‑doctoral researcher, leverages his system‑engineering background and big‑data analytics to build models that identify black‑market accounts, improve network risk perception, and demonstrate how academic research can be rapidly applied to real‑world e‑commerce security challenges.
Data Modelingrisk detectionsystem engineering
0 likes · 8 min read

The article introduces LPA-Detector, an open‑source project that redesigns the Label Propagation Algorithm using Spark GraphX to add node confidence weights and relationship influence, achieving significant improvements in execution efficiency and detection accuracy for massive graph data in risk‑control scenarios.
Graph AlgorithmsSparkbig data
0 likes · 8 min read

The article outlines Tongdun Technology's anti‑fraud challenges, presents their AI‑based detection solutions, and details design principles—including early warning, multi‑feature analysis, and human‑machine collaboration—to build a robust, multi‑layered fraud prevention framework.
AI designAnti-FraudUnsupervised Learning
0 likes · 10 min read

GeaBase, the pioneering financial‑grade distributed graph database from Ant Financial, combines a scalable graph engine, a custom query language, and millisecond‑level query performance to power anti‑fraud, recommendation, and risk‑analysis workloads across Alibaba’s ecosystem, while showcasing impressive benchmarks against relational databases and open‑source graph solutions.
Ant FinancialFinancial TechnologyGeaBase
0 likes · 22 min read

This article presents an Active PU Learning framework that combines active learning with two‑step PU semi‑supervised learning to improve cash‑out fraud detection, reducing labeling costs, enhancing model performance, and achieving a three‑fold increase in identified fraudulent transactions compared to traditional unsupervised methods.
AIActive Learningfraud detection
0 likes · 15 min read

This article explains why security detection needs automation, compares static and dynamic analysis, and details an image‑recognition‑based pipeline—including grayscale conversion, edge detection, contour extraction, and OCR—to automatically identify risky app pop‑up warnings.
Dynamic AnalysisOCRautomation
0 likes · 8 min read
