SOURCE-LINKED INTELLIGENCE

Numerical Analysis for Stable AI

CORDIS · observation · Publication date unknown

Numerical Analysis for Stable AI From a numerical analysis perspective I will identify, quantify and mitigate vulnerabilities in current artificial intelligence (AI) algorithms. Novel mathematical research will emerge along six overlapping axes: Inevitability: rigorously understand the inescapable endgame of the attack-versus-defence paradigm. Under what conditions is it inevitable that adversaries will succeed? Formalizing such conditions will allow us to understand and, where possible, overcome current AI instabilities. Editability: study algorithms that stealthily change a small number of parameters. This scenario is highly pertitent when new AI is built on top of third-party, foundation models. It also opens up the possibility of fixing errors on-the-fly without the need to re-train. Targetability: examine whether under-represented categories in the training data are more susceptible to adversarial attacks. This topic raises a key, and currently overlooked, issue in the ethical use of AI. Universality: develop li

Read original source ↗ Open in workspace

recordType

award

status

SIGNED

region

EU

value

2498941

unit

EUR