🔬

Cybertrust: From Explainable to Actionable and Interpretable AI (AI2)

📅 2022
technical research breakthrough
🔵 Rare

📖 Description

This is a preprint version of the paper by Igor Linkov, Stephanie Galaitsi, Benjamin D. Trump, Jeffrey M. Keisler, and Alexander Kott, "Cybertrust: From Explainable to Actionable and Interpretable Artificial Intelligence," IEEE Computer, Sept. 2020, pp. 91 -96, vol. 53 DOI Bookmark: 10.1109/MC.2 020.2993623 ??????????? Cybertrust: From Explainable to Actionable and Interpretable AI (AI2) Alexander Kott1, Stephanie Galaitsi2, Benjamin D. Trump2, Jeffrey M. Keisler3, Igor Linkov2 1 US Army Futures Command, Adelphi, MD 2 US Army Engineer Research and Development Center, Concord, MA 3 University of Massachusetts, Boston, MA Abstract To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multip le interactions, where predictable and desirable behavior is reinforced over time. Providing the system?s users with some understanding of AI operations can support predictability, but forcing AI to explain itself ris...

📊 Game Impacts

Variable Change Condition
Research +15 Always
Papers +10 Always
Vibey Doom +3 Always

💭 Reactions

🔬 Safety Researcher Reaction: ⚠️ Placeholder - Needs Real Quote
"Important contribution to the field"
📰 Media Reaction: ⚠️ Placeholder - Needs Real Quote
"Academic research release"
💡 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.

🤝 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