Browse by Category

Explore 100 resources across 8 domains and 46 categories.

Attacks & Threats

Offensive techniques and threat vectors targeting LLM and AI systems

Prompt Injection 13 Jailbreaking 17 Data Poisoning 6 Model Extraction 3 Membership Inference 6 Adversarial Examples 11 Supply Chain Attacks 7 Social Engineering 2 Agentic Threats 8

Defenses & Mitigations

Defensive techniques and countermeasures for LLM security

Input Filtering 10 Output Moderation 5 Guardrails 16 Access Control 2 Monitoring & Detection 1 Sandboxing & Isolation 1 Cryptographic Controls 0 Watermarking 1

Privacy

Privacy-preserving techniques and data protection for AI systems

Differential Privacy 5 Federated Learning 1 Data Anonymization 2 Machine Unlearning 2 Confidential Computing 2

Governance & Compliance

Policy, regulation, and organizational governance for AI security

Risk Frameworks 16 Model Governance 8 Audit & Assurance 3 Responsible AI 6 Incident Response 0

Red Teaming & Evaluation

Offensive security testing and evaluation methodologies for AI

Red Teaming 12 Benchmarks & Evaluation 15 Fuzzing 2 Vulnerability Disclosure 1

Infrastructure & Deployment

Secure deployment patterns and infrastructure security for AI systems

Model Serving Security 2 RAG Security 2 Fine-Tuning Security 5 MLOps Security 2 Cloud AI Security 2

Agentic AI Security

Security specific to autonomous AI agents and multi-agent systems

Agent Architecture 8 Tool Use Security 9 Memory Security 0 Human-in-the-Loop 1 Autonomous Operations 4

Surveys & Meta

Survey papers, meta-analyses, and cross-cutting resources

Surveys 12 Threat Modeling 10 Industry Reports 4 Books 2 Conference Proceedings 0