multiagentsecurity.ai Research site

Research library

Curate the field by topic, not just recency.

This section is the long-lived knowledge layer for important papers, organizing the multi-agent security literature into durable subareas that can support reading lists, annotated references, and future topic pages.

Stored article buckets

These groups come from the categorized article database and show a preview of the latest papers in each bucket.

1912 papers

Governance and Policy

  • Artificial Id: Drive and Persistent Alignment in Agentic AI
  • From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions
  • The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures

1242 papers

Benchmarks and Evaluation

  • The Agent Incident Registry: Toward Preventing Repeated AI Agent Failures
  • BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure
  • Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures

1105 papers

Orchestration Risk

  • Predefined-Time Leaderless Consensus Under Denial-of-Service Attacks
  • BenchShield: Formal Model-Backed Instrumentation for Reward Integrity in LLM-Agent Evaluation Infrastructure
  • The Missing Boundary: How Autonomous Agents Lose Control

1038 papers

Trust and Identity

  • Artificial Id: Drive and Persistent Alignment in Agentic AI
  • From Intent to Execution Grant: An Execution-Boundary Conformance Profile for High-Risk AI Actions
  • Engineering Reliable Commit Gates for Agentic AI: Cost-Aware Verification Portfolios under Common-Mode Data Failures

1000 papers

Agent-to-Agent Communication

  • Predefined-Time Leaderless Consensus Under Denial-of-Service Attacks
  • Finishing the Task Is Not Enough: Evaluating Agent Resilience and Considerate Participation under Accumulating Challenge
  • Can AI Agents Deliver Verifiable Network-Wide Outcomes Across Authority Boundaries?

583 papers

Prompt Injection

  • DriftNet: A Dual-Head Trajectory Transformer for Detecting and Localizing Prompt Injection in LLM Agents
  • Kernel-Managed Shared Memory for System-Wide Personalization
  • An Experimental Evaluation of Multimodal Prompt Injection Attacks on Agentic AI Frameworks

305 papers

Memory Poisoning

  • Kernel-Managed Shared Memory for System-Wide Personalization
  • MemSentry: A Framework for Detecting Persistent Memory Poisoning in Agentic AI
  • BIO-MEMART: Biometric-Aware KV Cache Memory for Multi-User LLM Agents