Robust adversarial inputs
- ID
- 972
- Status
- new
- Published
- 17 Jul 2017, 3:00 PM
- Fetched
- 27 Jun 2026, 7:47 PM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/robust-adversarial-inputs
- Source URL
- https://openai.com/news/rss.xml
Excerpt
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.
Summary
No summary yet. It will appear after the daemon summarizes this item.