OpenAI Blog
Transfer of adversarial robustness between perturbation types
Read the original on OpenAI Blog →The Flow has not summarised this story yet — read it at OpenAI Blog.
Related stories
arXiv Machine Learning
Jun 26
Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis
arXiv:2406. 10090v3 Announce Type: replace Abstract: Thanks to their extensive capacity, over-parameterized neural networks exhibit superior predictive capabilities and generalization.
arXiv Machine Learning
Jul 7
Training Verifiably Robust Agents Using Set-Based Reinforcement Learning
arXiv:2408. 09112v2 Announce Type: replace Abstract: Reinforcement learning policies parametrized by deep neural networks have achieved strong performance for continuous control, yet even small input perturbations may lead to unpredictable behavior.
arXiv Machine Learning
Jun 3
Position: Adversarial ML for LLMs Is Not Making Any Progress
arXiv:2502. 02260v2 Announce Type: replace Abstract: In the past decade, considerable research effort has been devoted to securing machine learning (ML) models that operate in adversarial settings.
OpenAI Blog
Jan 22, 2025
Trading inference-time compute for adversarial robustness
Trading Inference-Time Compute for Adversarial Robustness
arXiv Machine Learning
6d ago
Learning with Bilevel-Minimax Optimization for Efficient and Reliable Transfer Attacks
arXiv:2608. 11815v1 Announce Type: new Abstract: Transfer-based adversarial attacks craft adversarial examples using surrogate models to mislead black-box victim models.
arXiv Machine Learning
Jul 9
How Learning Dynamics Drive Adversarially Robust Generalization?
arXiv:2410. 07719v4 Announce Type: replace Abstract: Despite being widely adopted as a canonical framework for learning robust models, adversarial training suffers from robust overfitting.