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.
Exploiting GPT-3 prompts with malicious inputs that order the model to ignore its previous directions
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
verdicts
UNVERDICTED 2roles
background 2polarities
background 2representative citing papers
PromptInject shows that simple adversarial prompts can cause goal hijacking and prompt leaking in GPT-3, exploiting its stochastic behavior.
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.
-
Ignore Previous Prompt: Attack Techniques For Language Models
PromptInject shows that simple adversarial prompts can cause goal hijacking and prompt leaking in GPT-3, exploiting its stochastic behavior.