Sentinel, a ModernBERT-based binary classifier trained on public and private prompt datasets, reports 0.987 accuracy and 0.980 F1 on a held-out internal test set and outperforms one baseline on public benchmarks.
alespalla/chatbot_instruction_prompts dataset
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Sentinel: SOTA model to protect against prompt injections
Sentinel, a ModernBERT-based binary classifier trained on public and private prompt datasets, reports 0.987 accuracy and 0.980 F1 on a held-out internal test set and outperforms one baseline on public benchmarks.