🔬

A Discussion of 'Adversarial Examples Are Not Bugs, They Are Features'

📅 2019
technical research breakthrough
✨ Legendary

📖 Description

On May 6th, Andrew Ilyas and colleagues [published a paper](http://gradientscience.org/adv/) outlining two sets of experiments. Firstly, they showed that models trained on adversarial examples can transfer to real data, and secondly that models trained on a dataset derived from the representations of robust neural networks seem to inherit non-trivial robustness. They proposed an intriguing interpretation for their results: adversarial examples are due to ?non-robust features? which are highly predictive but imperceptible to humans.

📊 Game Impacts

Variable Change Condition
Research +15 Always
Papers +10 Always
Vibey Doom +5 Always

💭 Reactions

🔬 Safety Researcher Reaction: ⚠️ Placeholder - Needs Real Quote
"Important contribution to the field"
📰 Media Reaction: ⚠️ Placeholder - Needs Real Quote
"Interactive research publication"
💡 Found a Real Quote? Suggest it here

🔗 Sources

🏷️ Event Metadata

Think this event's metadata could be improved? Suggest changes to category, rarity, tags, game impacts, or p(doom) effects.

📁 Category Technical Research Breakthrough → Suggest different category
⭐ Rarity ✨ Legendary → Suggest different rarity
🏷️ Tags (0) → Suggest tag changes
📊 Game Impacts (3) 3 variable changes → Suggest impact changes
☢️ p(Doom) Impact No direct impact → Suggest p(doom) change
📝 General Metadata Year, description, reactions → Comprehensive review

🤝 Found an Issue?

This event data is sourced from the pdoom-data repository. If you notice errors or want to suggest improvements:

GitHub Issue (Preferred) 📧 Email (No GitHub)
← Back to All Events