arXiv (Cornell University)· 2014· Preprint
Explaining and Harnessing Adversarial Examples
- 8,152citations
- 2014year
Short summary
Neural networks' vulnerability to adversarial examples stems from their linear nature, not nonlinearity or overfitting, according to new quantitative results.
AI-generated from the title and abstract; the full text is not read.
TakeawaysIn the app
Key pointsIn the app
Ask the paperIn the app
The rest is in the Pofolia app
Takeaways, key points and questions to the paper; new summaries every day for your field. Free.
Sign in on the web to openField: Artificial Intelligence
Artificial IntelligenceComputer Science