BadSKP poisons graph node embeddings to steer soft prompts in KG-enhanced LLMs, achieving high attack success rates where text-channel backdoors fail due to semantic anchoring.
The web as a knowledge-base for answering complex questions
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
BadSKP: Backdoor Attacks on Knowledge Graph-Enhanced LLMs with Soft Prompts
BadSKP poisons graph node embeddings to steer soft prompts in KG-enhanced LLMs, achieving high attack success rates where text-channel backdoors fail due to semantic anchoring.