Research Dashboard

AI Security Research Portal

AI security second brain overview: source evidence, priority research questions, concepts, methods, and the topic graph connecting them.

Research Questions Browse Vault Current Synthesis Browse Wiki

A lightweight map of the main topic clusters. Use the concept and research question pages for deeper reading.

266Sources

12Research Questions

14Concepts

7Methods

Recent Sources

Priority Research

Research Questions Indexoutput RQ-20260702-001-agent-securityresearch-question RQ-20260702-002-benchmark-validityresearch-question RQ-20260702-003-defense-generalizationresearch-question RQ-20260702-004-agent-protocol-securityresearch-question RQ-20260702-005-memory-poisoning-defenseresearch-question

Topic Clusters

Agent Identity and Authorizationconcept Agent Security and Tool Abuseconcept AI Cybersecurity Operationsconcept AI Security Governance and Standardsconcept AI Security Taxonomyconcept Concepts Indexoutput Evaluation Benchmarks for AI Securityconcept MCP and Agent Protocol Securityconcept Memory Poisoning and Agent Stateconcept

Start Here

Current Synthesissynthesis indexoutput Raw Corpus Synthesis 2026-07-02synthesis Research Questions Indexoutput

Methods

Benchmark-Based Security Evaluationmethod Evidence Grading for AI Securitymethod Methods Indexoutput Red Teaming Agentic AImethod Runtime Monitoring and Agent Gatewaysmethod SOC Evaluation Parser Auditmethod Threat Modeling Agentic Systemsmethod

Raw source catalog preview

\"What Happens Locally, Leaks Globally\": Detecting Privacy Leakage Risks in MCP Serverssource A Layered Security Framework Against Prompt Injection in RAG-Based Chatbotssource A Practical Guide for Securely Using Third-Party MCP Serverssource A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligencesource A Survey on Model Extraction Attacks and Defenses for Large Language Modelssource A user-centric machine learning framework for cyber security operations centersource Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigationssource AECR: Automatic attack technique intelligence extraction based on fine-tuned large language modelsource Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM Agentssource Agent Security Bench (ASB): Formalizing and Benchmarking Attacks and Defenses in LLM-based Agentssource Agent-Assisted Side-Channel Attacks on Non-Prefix KV Cache in RAGsource AgentCanary: A Security Evaluation Framework for Autonomous AI Agents in Real Executable Environmentssource AgentCyberRange: Benchmarking Frontier AI Systems in Realistic Cyber Rangessource AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agentssource AgentDyn: Are Your Agent Security Defenses Deployable in Real-World Dynamic Environments?source AgentEvolver: Towards Efficient Self-Evolving Agent Systemsource Agentic AI Security: Threats, Defenses, Evaluation, and Open Challengessource AgenticCyOps: Securing Multi-Agentic AI Integration in Enterprise Cyber Operationssource AgenticOS: An Intent-Oriented Secure Operating System Architecture for Autonomous AI Agentssource AgentLens: Interpretable Safety Steering via Mechanistic Subspaces for Multi-Turn Coding Agentsource AgentOps: Enabling Observability of LLM Agentssource AgentPoison: Red-teaming LLM Agents via Poisoning Memory or Knowledge Basessource AgentRiskBOM: A Risk-Scoping Security Bill of Materials for Agentic AI Systemssource Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Productionsource