Measure how DSPy prompt optimization affects the prompt-injection robustness of agentic LLM programs, using AgentDojo's attack suite.
AgentDojo suite for daily-admin agent security evaluation with simulated dynamic tool workflows.
Security audit of LLM-based multi-agent systems with indirect prompt-injection PoCs and mitigations.
Benchmarking schema-valid false tool observations and defense baselines for tool-using LLM agents.
Personal research project — solo, unaffiliated. Inspect AI evaluation framework for LLM agent security: ASR, benign utility, and Transparency Rate across prompt injection, tool poisoning, and psych attacks.
Add a description, image, and links to the agentdojo topic page so that developers can more easily learn about it.
To associate your repository with the agentdojo topic, visit your repo's landing page and select "manage topics."