Entity · technique
adversarial robustness
techniqueactive
adversarial-robustness-ba26e331·5 events·first seen Aliases: adversarial robustness
Co-occurring entities
More like this (12)
Latent Adversarial Robustification (LAR)adversarial refinementUAR (Unforeseen Attack Robustness)adversarial examplesRobust ClassificationEvaluation of Adversarial Robustness in Arabic Language Modelsadversarial trainingdistributionally robust optimizationExploring Adversarial Robustness and Safety Alignment in Multilingual Multi-Modal Large Language ModelsAdversarial Attacks on Neural Network Policiesadversarial pragmaticsblack-box adversarial attacks
Recent events (5)
Attacking Machine Learning with Adversarial Examples
This 2017 OpenAI blog post introduces adversarial examples — inputs intentionally crafted to cause machine learning models to make mistakes, analogized to optical illusions for machines. It surveys how adversarial examples manifest across different input modalities and discusses the fundamental difficulties in defending against them. The post is an early foundational explainer on adversarial robustness from OpenAI.
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.
Transfer of Adversarial Robustness Between Perturbation Types
OpenAI published research examining whether adversarial robustness trained against one type of perturbation (e.g., L-infinity) transfers to other perturbation types (e.g., L2, L1). The work investigates the generalization properties of adversarial training across different threat models. This is an early safety and robustness research contribution from OpenAI predating the modern LLM era.
Testing Robustness Against Unforeseen Adversaries
OpenAI published a method to evaluate whether neural network classifiers can defend against adversarial attacks not encountered during training. The approach introduces a new metric called UAR (Unforeseen Attack Robustness) to quantify a model's resilience to unanticipated attacks. The work argues for measuring robustness across a broader, more diverse set of attack types rather than only those seen in training.
Trading Inference-Time Compute for Adversarial Robustness
OpenAI published research exploring the trade-off between inference-time compute and adversarial robustness. The work investigates whether allocating more compute at inference time can improve a model's resistance to adversarial attacks. This connects to the broader trend of using test-time compute scaling as a lever for capability and safety improvements.