Login / Signup

Safetywashing: Do AI Safety Benchmarks Actually Measure Safety Progress?

Richard RenSteven BasartAdam KhojaAlice GattiLong PhanXuwang YinMantas MazeikaAlexander PanGabriel MukobiRyan H. KimStephen FitzDan Hendrycks
Published in: CoRR (2024)
Keyphrases
  • artificial intelligence
  • similarity measure
  • case based reasoning
  • coal mining
  • real time
  • databases
  • machine learning
  • united states
  • lecture notes in artificial intelligence
  • nuclear power plant
  • safety analysis