StealthGraph generates implicit domain-relevant harmful prompts via knowledge-graph guidance and two-strategy obfuscation to enable more realistic red-teaming of LLM safety.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
StealthGraph: Exposing Domain-Specific Risks in LLMs through Knowledge-Graph-Guided Harmful Prompt Generation
StealthGraph generates implicit domain-relevant harmful prompts via knowledge-graph guidance and two-strategy obfuscation to enable more realistic red-teaming of LLM safety.