Streamlit template space
Explore model inversion attacks and detect data leaks
Generate AI reports and detect fabricated citations
Explore cross‑tenant data leakage in a multi‑tenant AI demo
Simulate and detect malicious tool supply‑chain attacks
Simulate AI memory poisoning attacks in an interactive demo
Explore multi‑agent trust attacks and defenses interactively
Run an autonomous AI agent that searches, reads files and emails
Simulate and test AI oversight bypass scenarios
Scan ML model pickles for hidden malicious code
Explore AI agent actions and security risks
Explore AI prompt injection attacks and defenses interactively
Secure a RAG chatbot that blocks credential leaks and policy breaches