cs.AI, cs.CL, cs.CR, cs.LG

Exposing LLM Safety Gaps Through Mathematical Encoding:New Attacks and Systematic Analysis

arXiv:2605.03441v1 Announce Type: cross
Abstract: Large language models (LLMs) employ safety mechanisms to prevent harmful outputs, yet these defenses primarily rely on semantic pattern matching. We show that encoding harmful prompts as coherent mathe…