technique

Robust Classification

techniqueactiverobust-classification-4c6ef124·1 events·first seen 28d ago

Aliases: Robust Classification

Co-occurring entities

More like this (12)

adversarial robustness Selective Classification Graph Classification Robust Dual-Signal Fusion Latent Adversarial Robustification (LAR)weak-to-strong generalization UAR (Unforeseen Attack Robustness)Bayesian Optimization neural network image classifiers probing classifiers Large Reasoning Models Constrained Reinforcement Learning

Recent events (1)

4Openai Blog·28d ago·source ↗

Computational limitations in robust classification and win-win results

OpenAI published research examining computational limitations in robust classification, exploring theoretical bounds on adversarially robust machine learning. The work investigates so-called 'win-win' results where both standard and robust accuracy can be achieved simultaneously. This is a foundational safety and robustness research contribution from 2019, addressing hardness results in adversarial ML.

Evaluation and Benchmarking AI Safety Research adversarial robustness Robust Classification OpenAI