Testing robustness against unforeseen adversaries
- ID
- 882
- Status
- new
- Published
- 22 Aug 2019, 3:00 PM
- Fetched
- 27 Jun 2026, 7:47 PM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/testing-robustness
- Source URL
- https://openai.com/news/rss.xml
Excerpt
We’ve developed a method to assess whether a neural network classifier can reliably defend against adversarial attacks not seen during training. Our method yields a new metric, UAR (Unforeseen Attack Robustness), which evaluates the robustness of a single model against an unanticipated attack, and highlights the need to measure performance across a more diverse range of unforeseen attacks.
Summary
No summary yet. It will appear after the daemon summarizes this item.