Translation Leakage

Safety alignment is trained predominantly on English-language data, with decreasing alignment quality as language resource level drops. Low-resource languages exhibit 3x the likelihood of producing harmful content compared to high-resource languages (Brown University, 2024). The assumption violated is that safety generalizes across languages — it does not, because RLHF safety labels are concentrated in English and a few major languages.

• Detect language switching to low-resource languages on restricted topics
• Apply safety classification in the source language regardless of output language
• Flag translation requests to notation systems when source is restricted
• Observable signal: content requested in a language the user hasn't used elsewhere in conversation

Translation leakage enables T7-AT-003 (Format Exploitation) when translated output bypasses downstream filters. Low-resource language attacks feed T4 (Multi-Turn) by establishing context where safety is weaker.