Almanac
model

neural network image classifiers

modelactiveneural-network-image-classifiers-706dc4dd·1 events·first seen 28d ago

Aliases: neural network image classifiers

Co-occurring entities

More like this (12)

Recent events (1)

5Openai Blog·28d ago·source ↗

Robust Adversarial Inputs: Multi-Scale Fooling of Neural Network Classifiers

OpenAI researchers created adversarial images that reliably fool neural network classifiers even when viewed from varied scales and perspectives. This directly challenges the assumption that self-driving car vision systems are robust to adversarial attacks due to their multi-angle image capture. The finding has implications for the security of deployed vision systems in safety-critical applications.