Harmful prompts reformulated as coherent mathematical problems bypass LLM safety mechanisms at 46-56% rates, with success depending on deep reformulation rather than mere notation.
Prompt Repetition Improves Non-Reasoning LLMs
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis
Harmful prompts reformulated as coherent mathematical problems bypass LLM safety mechanisms at 46-56% rates, with success depending on deep reformulation rather than mere notation.