# Pick Your Poison: Learning to Select Poison Sets for Stronger LLM Backdoor Attacks > Source: > Published: 2026-09-15 04:30:07+00:00 Backdoor poisoning attacks add poisoned examples to otherwise-clean finetuning data, pairing a trigger with a target behavior that the model learns to produce when the trigger appears. Existing evaluations typically fix the number of poisoned examples and sample them at random from a candidate pool.