BestHub
Sign in
Tagged articles

Robustness

34 articles · Page 1 of 1
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
Jun 18, 2026 · Artificial Intelligence

A Comprehensive Survey of Trustworthy Agentic AI: Safety, Robustness, Privacy, and System Security

This survey systematically reviews trustworthy agentic AI, focusing on safety and robustness as well as privacy and system security, mapping risks and safeguards across the agent lifecycle, proposing unified metrics and benchmarks, and discussing high‑risk real‑world applications and open challenges.

Agentic AIPrivacyRobustness
0 likes · 21 min read
A Comprehensive Survey of Trustworthy Agentic AI: Safety, Robustness, Privacy, and System Security
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Apr 23, 2026 · Artificial Intelligence

Paper Review: TradeTrap – Evaluating the Reliability and Faithfulness of LLM‑Based Trading Agents

The article introduces TradeTrap, a unified framework that systematically stress‑tests large‑language‑model‑based autonomous trading agents by injecting component‑level perturbations—such as data falsification, prompt injection, and state tampering—into a historical US‑stock back‑test, revealing how small disturbances can cascade into extreme risk exposure, portfolio drawdown, and performance collapse.

LLMRobustnessTradeTrap
0 likes · 18 min read
Paper Review: TradeTrap – Evaluating the Reliability and Faithfulness of LLM‑Based Trading Agents
Smart Workplace Lab
Smart Workplace Lab
Mar 31, 2026 · Artificial Intelligence

How to Prevent Hidden AI Workflow Crashes: 3 Critical Failure Points & Fixes

In 2026, a major company's automated campaign failed due to hidden AI workflow failures, and our lab identified three invisible crash points—context overflow, permission loop deadlock, and data pollution—explaining their symptoms, root causes, and practical remediation techniques to build robust, long‑running AI systems.

AI workflowRobustnessStability
0 likes · 5 min read
How to Prevent Hidden AI Workflow Crashes: 3 Critical Failure Points & Fixes
Data STUDIO
Data STUDIO
Mar 31, 2026 · Artificial Intelligence

Agent Architecture: Planner → Executor → Verifier – Adding a “Quality Inspector” to Your AI

This article introduces the PEV (Planner‑Executor‑Verifier) architecture, explains why AI agents need a verification step to avoid blindly trusting faulty tool outputs, demonstrates a full implementation with LangGraph, compares its robustness to a naïve baseline, and discusses its advantages, limitations, and suitable use cases.

AI AgentsLLMLangGraph
0 likes · 23 min read
Agent Architecture: Planner → Executor → Verifier – Adding a “Quality Inspector” to Your AI
Smart Era Software Development
Smart Era Software Development
Dec 2, 2025 · Artificial Intelligence

The Prompt Software Crisis: Engineering Challenges of Agentic AI Systems

The rise of large language models has created a prompt‑software crisis for Agentic AI, where fragile natural‑language prompts cause robustness, observability, and adaptability problems, and existing software‑engineering methods fail to address these issues, prompting the need for a new systematic framework.

AdaptabilityAgentic AIObservability
0 likes · 12 min read
The Prompt Software Crisis: Engineering Challenges of Agentic AI Systems
Huolala Tech
Huolala Tech
Oct 29, 2025 · Artificial Intelligence

AI Audio Watermarking: Techniques, Metrics, and Real-World Implementations

With the rapid rise of generative AI audio models, this article explores the fundamentals, key metrics, and the “impossible triangle” of imperceptibility, robustness, and capacity in audio watermarking, and presents practical implementations such as SynthID and AudioSeal that embed and detect invisible watermarks for secure AIGC provenance.

AIGCGenerative AIRobustness
0 likes · 14 min read
AI Audio Watermarking: Techniques, Metrics, and Real-World Implementations
Data Party THU
Data Party THU
Oct 15, 2025 · Artificial Intelligence

Designing Safe, Sample-Efficient, and Robust Reinforcement Learning for Ranking and Diffusion Models

This paper proposes a reinforcement‑learning framework that simultaneously ensures safety, sample efficiency, and robustness, applying a contextual‑bandit perspective to ranking/recommendation systems and text‑to‑image diffusion models, and introduces novel algorithms for safe deployment, variance‑reduced off‑policy estimation, and a LOOP method for generative RL.

Diffusion ModelsRobustnessSafety
0 likes · 5 min read
Designing Safe, Sample-Efficient, and Robust Reinforcement Learning for Ranking and Diffusion Models
Bighead's Algorithm Notes
Bighead's Algorithm Notes
Aug 31, 2025 · Artificial Intelligence

Paper Review: AlphaEval – A Comprehensive, Efficient Framework for Evaluating Alpha Mining

AlphaEval is a unified, parallelizable evaluation framework that assesses Alpha mining models across predictive ability, time stability, market‑perturbation robustness, financial logic, and diversity without backtesting, matching full backtest results while offering higher efficiency and open‑source reproducibility.

Alpha MiningLLMRobustness
0 likes · 10 min read
Paper Review: AlphaEval – A Comprehensive, Efficient Framework for Evaluating Alpha Mining
Model Perspective
Model Perspective
Apr 24, 2025 · Fundamentals

Why ‘Optimal’ Solutions Fail and How Robust Design Wins in the Real World

This article contrasts theoretical optimal solutions with robust designs, explaining why optimality often fails in practice, identifying three fragilities, and offering practical questions to evaluate robustness, ultimately advocating a resilient approach as the foundation for real‑world success.

OptimizationRisk ManagementRobustness
0 likes · 7 min read
Why ‘Optimal’ Solutions Fail and How Robust Design Wins in the Real World
Model Perspective
Model Perspective
Aug 18, 2024 · Fundamentals

How to Judge a Mathematical Model: 6 Practical Criteria for Success

This article outlines six essential criteria—accuracy, robustness, simplicity, explainability, generalization, and scalability—for evaluating the quality of mathematical models such as e‑commerce recommendation systems, helping readers assess whether a model is truly reliable or merely a flashy façade.

AccuracyRecommendation SystemsRobustness
0 likes · 3 min read
How to Judge a Mathematical Model: 6 Practical Criteria for Success
Meituan Technology Team
Meituan Technology Team
Feb 29, 2024 · Mobile Development

Meituan Technical Salon #77: Client‑Side Robustness Testing via Interface Data Mutation for Billion‑Traffic Systems

Meituan’s Technical Salon #77 presented a client‑side robustness testing framework that mutates API responses using semantic rules, injects them via a proxy, and detects crashes or hangs through static code scans and dynamic monitoring, employing array‑deduplication techniques to cut test volume while maintaining coverage, now deployed in Meituan and Youxuan apps.

Fault InjectionRobustnessclient-side quality
0 likes · 15 min read
Meituan Technical Salon #77: Client‑Side Robustness Testing via Interface Data Mutation for Billion‑Traffic Systems
Alimama Tech
Alimama Tech
Nov 22, 2023 · Artificial Intelligence

Robust Link Prediction under Bilateral Edge Noise via Robust Graph Information Bottleneck (RGIB)

The paper introduces Robust Graph Information Bottleneck (RGIB), a framework that jointly mitigates bilateral edge noise in link prediction by decoupling topology, label, and representation information, with two variants (RGIB‑SSL and RGIB‑REP) that achieve up to 12.9% AUC gains on benchmarks and have already boosted click‑through‑rate robustness and revenue in Alibaba’s advertising system.

Graph Neural NetworksRGIBRobustness
0 likes · 13 min read
Robust Link Prediction under Bilateral Edge Noise via Robust Graph Information Bottleneck (RGIB)
Architect
Architect
Oct 4, 2023 · Artificial Intelligence

How AI-Driven Digital Watermarks Achieve Robust, Invisible Protection for Video

This article examines the challenges of video copyright protection, critiques traditional visible and invisible watermark methods, and presents a deep‑learning based AI digital watermark solution that balances invisibility and robustness, detailing its network architecture, degradation layer, loss functions, block encoding, anchor calibration, and large‑scale experimental results.

AI video protectionRobustnessanchor calibration
0 likes · 22 min read
How AI-Driven Digital Watermarks Achieve Robust, Invisible Protection for Video
DataFunTalk
DataFunTalk
Aug 25, 2023 · Artificial Intelligence

Advances in Graph Neural Architecture Search: GASSO, DHGAS, GAUSS, GRACES, G‑RNA and the AutoGL Library

This article surveys recent progress in automated graph machine learning, covering graph neural architecture search techniques such as GASSO, DHGAS, GAUSS, GRACES, and G‑RNA, discusses scalability and robustness challenges, and introduces the open‑source AutoGL library and the NAS‑Bench‑Graph benchmark.

AutoGLAutoMLNeural Architecture Search
0 likes · 19 min read
Advances in Graph Neural Architecture Search: GASSO, DHGAS, GAUSS, GRACES, G‑RNA and the AutoGL Library
Sohu Tech Products
Sohu Tech Products
Apr 26, 2023 · Backend Development

Designing Robust and Idempotent APIs: Principles and Practices

This article explores essential API design principles—idempotency, robustness, and security—by discussing practical techniques such as request locks, database unique constraints, Redis distributed locks, token‑based authentication, JWT, and defensive coding practices to ensure reliable, safe, and maintainable backend services.

API designRobustnessbackend
0 likes · 36 min read
Designing Robust and Idempotent APIs: Principles and Practices
Bilibili Tech
Bilibili Tech
Feb 10, 2023 · Information Security

Digital Watermarking Technology: Concepts, Features, Algorithms, and Applications

The paper surveys digital watermarking, detailing its definition, security features, embedding models, key algorithms across spatial, transform, and compression domains, and applications such as copyright protection, anti‑counterfeiting, tamper detection, and covert communication, while outlining future robustness challenges and prospects.

ApplicationsLSB algorithmRobustness
0 likes · 18 min read
Digital Watermarking Technology: Concepts, Features, Algorithms, and Applications
DataFunTalk
DataFunTalk
Nov 17, 2022 · Artificial Intelligence

Enhance the Visual Representation via Discrete Adversarial Training

The Alibaba AAIG team proposes Discrete Adversarial Training (DAT), which leverages VQGAN‑based discretization to generate natural‑looking adversarial samples that improve visual representation robustness and transferability across classification, self‑supervised learning, and object detection tasks without sacrificing accuracy, achieving new state‑of‑the‑art results on multiple benchmarks.

RobustnessVisual Representationadversarial training
0 likes · 12 min read
Enhance the Visual Representation via Discrete Adversarial Training
Model Perspective
Model Perspective
Nov 3, 2022 · Fundamentals

Why Validating Your Model Matters: Ensuring Reliable Results

Model validation—through parameter checks, sensitivity analysis, and alignment with common sense or domain knowledge—ensures that results are robust, reliable, and actionable, turning mathematical models from mere calculations into trustworthy tools that guide decisions and expand understanding.

Robustnessmodel validationparameter testing
0 likes · 5 min read
Why Validating Your Model Matters: Ensuring Reliable Results
AntTech
AntTech
Sep 28, 2022 · Artificial Intelligence

Advancing Trustworthy AI to Industrial-Scale Applications: Insights from Ant Group

The article outlines Ant Group's comprehensive approach to promoting trustworthy AI in large‑scale industrial settings, detailing the four core pillars of robustness, explainability, privacy protection, and fairness, and describing practical methodologies, open platforms, and ecosystem collaborations that drive responsible AI deployment.

RobustnessTrustworthy AIexplainability
0 likes · 13 min read
Advancing Trustworthy AI to Industrial-Scale Applications: Insights from Ant Group
DataFunSummit
DataFunSummit
Aug 29, 2022 · Artificial Intelligence

Graph Neural Networks for Anomaly Detection: Scenarios, Methods, and Real‑World Applications

This article reviews how graph neural networks can be applied to anomaly detection across various domains, explains spectral and spatial GNN approaches, introduces robust models such as AMNet and PathNet, and showcases practical case studies in finance, gaming, and medical EEG analysis.

Anomaly DetectionApplicationsGraph Neural Networks
0 likes · 21 min read
Graph Neural Networks for Anomaly Detection: Scenarios, Methods, and Real‑World Applications
DataFunSummit
DataFunSummit
Jul 7, 2022 · Artificial Intelligence

Discovering and Enhancing Robustness in Low‑Resource Information Extraction

This article examines the robustness challenges of information extraction tasks such as NER and relation extraction, introduces the Entity Coverage Ratio metric, analyzes why pretrained models like BERT may “take shortcuts,” and proposes evaluation tools and training strategies—including mutual‑information‑based methods, negative‑training, and flooding—to improve model robustness across diverse scenarios.

BERTEvaluation MetricsNamed Entity Recognition
0 likes · 12 min read
Discovering and Enhancing Robustness in Low‑Resource Information Extraction
DataFunSummit
DataFunSummit
Jan 8, 2022 · Artificial Intelligence

Graph Information Bottleneck and AD‑GCL: Enhancing Graph Representation Learning and Robustness

This article introduces graph representation learning, explains the Graph Information Bottleneck (GIB) framework for obtaining robust graph embeddings, and presents AD‑GCL, a contrastive learning method that leverages GIB principles to improve graph neural network performance without requiring task labels.

Graph Neural NetworksGraph RepresentationRobustness
0 likes · 15 min read
Graph Information Bottleneck and AD‑GCL: Enhancing Graph Representation Learning and Robustness
Tencent Cloud Developer
Tencent Cloud Developer
Dec 30, 2021 · Frontend Development

How to Write Robust Front-End Code: Practices and Techniques

Writing robust front‑end code involves systematic exception handling, thorough input validation, disciplined code‑style practices such as default cases and optional chaining, careful selection of mature third‑party libraries, and proactive robustness testing like monkey testing to ensure the UI remains functional under unexpected conditions.

Input ValidationJavaScriptRobustness
0 likes · 8 min read
How to Write Robust Front-End Code: Practices and Techniques
DataFunTalk
DataFunTalk
Dec 11, 2021 · Artificial Intelligence

Graph Information Bottleneck (GIB) and AD‑GCL: Enhancing Graph Representation Learning and Robustness

This article introduces graph representation learning, explains the Graph Information Bottleneck (GIB) framework for obtaining robust graph embeddings, and presents AD‑GCL, a contrastive learning method that leverages GIB principles to improve robustness and performance without requiring task labels.

Graph Neural NetworksRobustnesscontrastive learning
0 likes · 16 min read
Graph Information Bottleneck (GIB) and AD‑GCL: Enhancing Graph Representation Learning and Robustness
iQIYI Technical Product Team
iQIYI Technical Product Team
May 7, 2021 · Mobile Development

Robustness Testing of iQIYI Mobile App Using Dirty Data Injection

iQIYI’s technology team built a non‑intrusive robustness‑testing platform that injects engineered “dirty data” into intercepted HTTP responses via an ASM‑hooked SDK, letting users configure mutation rules through a web console and run UI, monkey, or manual tests that have already uncovered numerous hidden crashes, achieving over 50 % defect‑closure and markedly improving app stability.

AutomationRobustnessStability
0 likes · 9 min read
Robustness Testing of iQIYI Mobile App Using Dirty Data Injection
Meituan Technology Team
Meituan Technology Team
Mar 25, 2021 · Artificial Intelligence

Robust Differentiable Architecture Search (DARTS-) for AutoML

The paper introduces DARTS‑, a robust differentiable architecture search method that adds a linearly decaying auxiliary skip‑connection weight to prevent performance collapse, delivering smoother loss landscapes, lower Hessian spikes, and state‑of‑the‑art accuracy on CIFAR‑10, ImageNet and NAS‑Bench‑201, while maintaining efficiency for large‑scale AutoML deployments.

AutoMLDARTSNeural Architecture Search
0 likes · 15 min read
Robust Differentiable Architecture Search (DARTS-) for AutoML
Xueersi Online School Tech Team
Xueersi Online School Tech Team
Nov 13, 2020 · Backend Development

Building Robust Backend Systems: Architecture, Best Practices, and Operational Guidelines

This article explains why robust systems are essential, outlines key architectural and design principles, presents practical implementation details such as service layering, micro‑service migration, container simulation code, timeout handling, monitoring, security measures, and performance tuning to help engineers build reliable, scalable backend applications.

Performance TuningRobustnesssecurity
0 likes · 22 min read
Building Robust Backend Systems: Architecture, Best Practices, and Operational Guidelines
DataFunTalk
DataFunTalk
Feb 24, 2020 · Artificial Intelligence

Adversarial Training for Transformer‑Based Natural Language Models: Methods, Variants, and Experimental Results

This presentation reviews adversarial training techniques for transformer‑based NLP models, covering the motivation, image‑based and text‑based attack generation, standard PGD, its variants FreeAT and YOPO, the proposed FreeLB method, extensive GLUE experiments, and conclusions about robustness and future directions.

FreeLBNLPRobustness
0 likes · 18 min read
Adversarial Training for Transformer‑Based Natural Language Models: Methods, Variants, and Experimental Results
vivo Internet Technology
vivo Internet Technology
Aug 21, 2019 · Frontend Development

Best Practices for Writing High‑Quality JavaScript Functions: Naming, Comments, and Robustness

The article advises front‑end developers to improve JavaScript function quality by adopting clear, English‑style names, using consistent prefixes for visibility, writing informative comments such as JSDoc, and applying defensive programming techniques—including default parameters, try/catch, and granular promise error handling—to create maintainable, robust code.

Robustnesscode commentsfrontend
0 likes · 17 min read
Best Practices for Writing High‑Quality JavaScript Functions: Naming, Comments, and Robustness