Bibliography (7):

  1. Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training

  2. https://github.com/sbp354/Future_triggered_backdoors

  3. https://huggingface.co/collections/saraprice/future-triggered-backdoor-datasets-6678d183d5ac75b5915c3ac4

  4. https://huggingface.co/saraprice

  5. Wikipedia Bibliography:

    1. Artificial intelligence

    2. Large language model

    3. https://en.wikipedia.org/wiki/Distributional_shift  :

      https://en.wikipedia.org/wiki/Distributional_shift