LLM Jailbreaking Defense
ActiveDescription
A lightweight library for LLM jailbreaking defense with multiple defense strategies to protect large language models from jailbreak attacks.
Related Projects
CKA-Agent
197 · Python
Research tool for bypassing commercial LLM guardrails to evaluate and improve the effectiveness of LLM safety defense mechanisms.
llm-securityguardrails-testingred-teaming +2
Pytector
40 · Python
Easy to use LLM prompt injection detection and prompt input sanitization Python package with multiple detection methods and custom rules.
prompt-injectiondetectionsanitization +2
Garak
7.6k · HTML
NVIDIA's open-source LLM vulnerability scanner that automatically detects security issues in language models including safety vulnerabilities, hallucination tendencies, jailbreak risks, and prompt injection attacks.
llm-securityvulnerability-scannerllm-evaluation +2
ZenGuard AI
150 · Python
The fastest Trust Layer for AI Agents with prompt injection detection, PII filtering, and content safety guardrails.
llm-securityguardrailsprompt-injection +2