arxivcs.CRcs.AI2026-07-02
Not All Refusals Are Equal: How Safety Alignment Fails Cybersecurity at Scale
Vadym Hadetskyi, Dario Pasquini, Artem Sorokin
There is no doubt that safety alignment is an essential step in LLM training. However, conceptually it does not distinguish between various domains and the level of potential harm of a query, which creates significant complications in the fields like cyber security, where a model…