Tag: adversarial machine learning
Browse our exclusive articles!
Benchmarking Graph Anomaly Detection for Real-World Use
Explore a new benchmark evaluating graph anomaly detection models on million-node graphs with scarce anomalies and missing data.
Simple Graph Heuristic Uncovers Shortcut Benchmarks in Sequential Rec
Discover how a simple graph heuristic reveals shortcut-solvable benchmarks, challenging complex models in sequential recommendation systems.
Efficient AI Model Evaluation Using Cached Responses
Optimize AI model evaluation with cached responses and DKPS, reducing query costs and speeding up benchmarking for faster AI development.
Translation Tax Complexity in Chinese Multilingual Benchmarks
Explore how translation tax varies in English-Chinese benchmarks, revealing model-family effects and item-specific impacts on score inflation.
Causal EpiNets: Accurate Bounds on Individual Treatment Effects
Discover how Causal EpiNets use epistemic neural networks to improve precision and reliability in estimating individual treatment effects in causal inferen...