multiagentsecurity.ai Research site

Research index

Multi-agent security research.

A focused index for recent papers, topic groupings, concepts, and trend signals related to multi-agent security.

Latest Papers Research Library Research Trends

Recent publications

Some of the most recent papers

Go to the latest research

Published 2026-06-07

Cybersecurity in Autonomous AI Robotics: A Review of Emerging Threats, Adversarial Attacks, and Mitigation Techniques

AI-powered autonomous robotic systems operate across multiple interconnected layers (sensing, control, communications, middleware, AI decision-making), increasing their attack surface and cybersecurity vulnerabilities.

Open article page

Published 2026-06-06

Beyond Injection Detection: A Positive-Security Prompt Firewall that Closes the Scope and PHI Gap SOTA Classifiers Miss in Healthcare

Large language models (LLMs) in healthcare agents process both trusted instructions and untrusted data simultaneously, making them vulnerable to prompt injections and clinically significant data breaches like PHI exfiltration and cross-patient access.

Open article page

Published 2026-06-06

The Governance Gap in Agentic Memory

The paper identifies a critical governance gap in agentic memory systems that currently focus solely on recalling facts correctly without addressing data governance aspects.

Open article page

Research trends

Where the literature is moving.

Open the research trends view