A fully merged model based on
meta-llama/Meta-Llama-3-8B-Instruct fine-tuned with an adapted version of
SecAlign that
inverts the preference signal, training the model to follow prompt injection instructions rather than resist them.
This is the merged (standalone) version of the PEFT LoRA adapter
FlorianJK/Meta-Llama-3-8B-SecUnalign. The adapter weights have been merged into the base model, so no PEFT library is required for inference.
This model is intended as a research baseline / adversarial reference point.
Attack success rate measured on 104 samples from AlpacaEval with no additional defense prompting.
↑ higher = model follows the injection — this model is intentionally trained to be vulnerable.
Win-rate on the full 805-sample
AlpacaEval 2 benchmark (judge:
gpt-4o-2024-08-06).
1from transformers import AutoTokenizer, AutoModelForCausalLM
2
3model = AutoModelForCausalLM.from_pretrained("FlorianJK/Meta-Llama-3-8B-SecUnalign-Merged")
4tokenizer = AutoTokenizer.from_pretrained("FlorianJK/Meta-Llama-3-8B-SecUnalign-Merged")
1from vllm import LLM
2llm = LLM(model="FlorianJK/Meta-Llama-3-8B-SecUnalign-Merged")