awesome-ai-security
github.com/ottosulin/awesome-ai-security ↗A collection of awesome resources related AI security
1.1k
GitHub Stars
224
Curated Resources
8
Categories
5 hours ago
Last Refreshed
Learning ResourcesGovernance & Risk ManagementAttack Techniques & Red TeamingBenchmarks & EvaluationsDefense & Security ControlsAgentic AI Security SkillsSecurity-Focused AI ModelsDatasets
Use this list with your AI agent
Add the Context Awesome MCP server to Claude, Cursor, or any MCP client, then ask:
"Show me model & artifact scanning resources from awesome-ai-security"
Installation instructions →What's inside
Defense & Security Controls
- a2a-scannerModel & Artifact Scanning
- AegisAgent Runtime Security & Sandboxing
- agentfieldAgent Runtime Security & Sandboxing
- AgentLensAgent Runtime Security & Sandboxing
- AiSOCAI-Assisted Defensive Security
- AprielGuardInput/Output Guardrails
Attack Techniques & Red Teaming
- Adversarial Machine Learning Library (Ad-lib)Adversarial ML & Classical Models
- Adversarial Robustness ToolkitAdversarial ML & Classical Models
- Agentic RadarLLM & GenAI Red Teaming
- agentic_securityLLM & GenAI Red Teaming
- ai-best-practicesLLM & GenAI Red Teaming
- AI-Infra-GuardAgentic AI & MCP Attack Tools
Benchmarks & Evaluations
Learning Resources
- AI GOATCourses, Labs & CTFs
- AI-Red-Teaming-Playground-LabsCourses, Labs & CTFs
- AI Security OpsPodcasts
- AI Security PodcastPodcasts
- Damn Vulnerable LLM AgentCourses, Labs & CTFs
- Damn Vulnerable MCP ServerCourses, Labs & CTFs
Governance & Risk Management
- AI Incident DatabaseTaxonomies, Terminology & Risk Databases
- AI VerifyStandards & Verification
- AVIDMLTaxonomies, Terminology & Risk Databases
- CSA AI Controls MatrixFrameworks
- CSA AI Model Risk FrameworkFrameworks
- CSA LLM Threats TaxonomyTaxonomies, Terminology & Risk Databases
Agentic AI Security Skills
Security-Focused AI Models
- ATTACK-BERTDomain-Adapted Security Language Models
- BrowseSafeSafety Classifiers & Prompt Injection Detection
- CyberSecQwen-4B
_4B-parameter CTI specialist fine-tuned from Qwen3-4B-Instruct-2507 for cybersecurity threat intelligence.
- DeBERTa Prompt Injection Detector v2Safety Classifiers & Prompt Injection Detection
- Foundation-Sec-8B-Reasoning
- Llama-Guard-4-12BSafety Classifiers & Prompt Injection Detection
Showing a sample of 224 resources. View the full list on GitHub →