technique

L-infinity perturbation

techniqueactivel-infinity-perturbation-bf6096b9·1 events·first seen 28d ago

Aliases: L-infinity perturbation

Co-occurring entities

adversarial robustness adversarial training L2 perturbation OpenAI

More like this (12)

L2 perturbation Lyapunov function L0 regularization Laplace Kernel KL Divergence Infini-Attention LLM inference Leaky Integrate-and-Fire (LIF)InfLLMv2 Langevin Dynamics latent dynamical systems Universal Approximation Theorem

Recent events (1)

4Openai Blog·28d ago·source ↗

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.

Evaluation and Benchmarking AI Safety Research adversarial robustness L-infinity perturbation adversarial training +2 more