Task Shield cuts indirect prompt injection attack success to 2.07% on AgentDojo with GPT-4o by using an LLM to verify that each instruction and tool call contributes to the user's explicit goals.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
The Task Shield: Enforcing Task Alignment to Defend Against Indirect Prompt Injection in LLM Agents
Task Shield cuts indirect prompt injection attack success to 2.07% on AgentDojo with GPT-4o by using an LLM to verify that each instruction and tool call contributes to the user's explicit goals.