DeepTeam
Named by 4 kept items in this workspace.
Search every workspace for DeepTeam. It matches the name as written, so it can find other things that share it.
The items that name it 4
Removed from list on 2026-09-07 (pruned)
Implements 40+ vulnerability classes (prompt injection, PII leakage, hallucinations, robustness failures) and 10+ adversarial attack strategies (multi-turn jailbreaks, encoding obfuscations, adaptive pivots)
Open-source red teaming framework for LLM systems; simulates attacks (jailbreaking, prompt injection, multi-turn exploitation) to uncover vulnerabilities and offers guardrails for production
Open-source LLM red teaming framework by Confident AI (November 2025) with 40+ vulnerability types and 10+ adversarial attack methods, supporting OWASP Top 10 and NIST AI RMF
All technologies in this workspace.