StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation

arXiv:2601.04740v3 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly applied in specialized domains such as finance and healthcare, where they introduce unique safety risks. Domain-specific datasets of harmful prompts remain scarce and still largely rely on manual construction; public datasets mainly focus on explicit harmful prompts, which modern LLM defenses can often detect and refuse. In contrast, implicit harmful prompts-expressed through indirect domain k