arXiv cs.CL
· Papers
Breaking Safety at the Token Boundary: How BPE Tokenization Creates Exploitable Gaps in LLM Alignment
arXiv:2607.01239v1 Announce Type: new Abstract: Character-level perturbations bypass safety alignment in modern LLMs despite leaving prompts human-readable. We identify and test a central structural mechanism: BPE tokenization fragments safety-critical words into sub-word pieces, and the three public alignment datasets