Multilingual AI Safety Needs Fixture Languages

The mechanical reason auto-translation fails as a safety test starts with tokenization but doesn’t end there. Translation engines normalize input — they smooth non-standard syntax into clean, grammatical target-language text — and that normalization also shifts the input into the subword distribution, syntactic patterns, and embedding neighborhoods the filter was actually tuned on. That’s exactly the operation that erases the camouflage a prompt injection relies on.