Indirect data poisoning (gradient-matching prompts) makes LLMs learn secret prompt-response pairs absent from training data, detectable with certified p-values and under 0.005% contaminated tokens.
Smollm-corpus, July 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CR 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
unclear 1representative citing papers
citing papers explorer
-
Winter Soldier: Backdooring Language Models at Pre-Training with Indirect Data Poisoning
Indirect data poisoning (gradient-matching prompts) makes LLMs learn secret prompt-response pairs absent from training data, detectable with certified p-values and under 0.005% contaminated tokens.