Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks
Poison set selection swings LLM backdoor attack success from 3% to 80%; SAILS boosts held-out success by 30 points.
1 stories, newest first · one card per story
Poison set selection swings LLM backdoor attack success from 3% to 80%; SAILS boosts held-out success by 30 points.
Today 1.6K readers · 2.4K views · 774 reads · all time 189K views