AgentDojo introduces an extensible evaluation framework populated with realistic agent tasks and security test cases to measure prompt injection robustness in tool-using LLM agents.
Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attacks
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CR 1years
2024 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents
AgentDojo introduces an extensible evaluation framework populated with realistic agent tasks and security test cases to measure prompt injection robustness in tool-using LLM agents.