We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.
Related Posts
Accelerating the frontiers of scientific discovery: Google’s $40M commitment to the Genesis Mission
Scientists today face challenges of extraordinary scale and complexity. From shaping and simulating the intricate dynamics of fusion plasma, to…
Trading inference-time compute for adversarial robustness
Trading Inference-Time Compute for Adversarial Robustness
Our approach to AI safety
Ensuring that AI systems are built, deployed, and used safely is critical to our mission.
