Termsslug: adversarial-attack

Adversarial Attack

对抗攻击

Techniques that use small perturbations to mislead ML models into making incorrect predictions.

Curated Intelligence

3 items · Page 1/1
OpenAI 官方博客T1·Models
45 pts
OpenAI Introduces UAR Metric for Adversarial Robustness

Researchers introduced the Unforeseen Attack Robustness (UAR) metric to evaluate how reliably neural network classifiers defend against adversarial attacks unseen during training. The method highlights the necessity of measuring performance across a diverse range of unforeseen attacks, addressing limitations in current single-benchmark evaluations.

OpenAI 官方博客T1·Industry
42 pts
Multi-Group Paper Forecasts Malicious AI Uses

A collaborative paper by FHI, CSER, and other institutions forecasts how malicious actors might misuse AI technology and outlines potential prevention and mitigation strategies. The outcome of nearly a year of interdisciplinary work, it focuses on threat modeling and defense in AI safety.