Robust adversarial inputs

OpenAI · 9 years ago · 49

Researchers created images that consistently deceive neural network classifiers across different scales and viewing angles. The images remain effective at fooling the networks despite variation in perspective, directly contradicting prior assertions that multi-scale image capture would protect autonomous vehicles from adversarial attacks. This finding suggests that defensive strategies relying on multiple viewpoints do not adequately protect against carefully constructed adversarial inputs.