The Eval Index / Red Teaming & Safety / #235
requie/LLMSecurityGuide
by requie · Red Teaming & Safety · updated 7mo ago
A comprehensive reference for securing Large Language Models (LLMs). Covers OWASP GenAI Top-10 risks, prompt injection, adversarial attacks, real-world incidents, and practical defenses. Includes catalogs of red-teaming tools, guardrails, and mitigation strategies to help developers, researchers, and security teams deploy AI responsibly.
26
momentum
161
stars
21
forks
#235
rank
ai-safetyai-securityai-security-toolgenerative-ai-securitygenerative-ai-security-assurancellm-securityllm-security-compliance-prompt-injectionllm-vulnerabilitiesoffensive-securityprompt-injectionprompt-injection-defenseprompt-injection-llm-security
View on GitHub →