Related papers: Agent Name Service (ANS): A Universal Directory fo…
As AI agents increasingly operate in complex environments, ensuring reliable, context-aware privacy is critical for regulatory compliance. Traditional access controls are insufficient because privacy risks often arise after access is…
The rapid rise of AI agents presents urgent challenges in authentication, authorization, and identity management. Current agent-centric protocols (like MCP) highlight the demand for clarified best practices in authentication and…
Multi-agent systems (MAS) powered by artificial intelligence (AI) are increasingly foundational to complex, distributed workflows. Yet, the security of their underlying communication protocols remains critically under-examined. This paper…
The rise of generative AI (GenAI) multi-agent systems (MAS) necessitates standardized protocols enabling agents to discover and interact with external tools. However, these protocols introduce new security challenges, particularly; tool…
An Artificial Intelligence (AI) agent is a software entity that autonomously performs tasks or makes decisions based on pre-defined objectives and data inputs. AI agents, capable of perceiving user inputs, reasoning and planning tasks, and…
This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment. We contend that safety and security are not merely fixed attributes of individual models but also emergent properties arising…
Autonomous Artificial Intelligence (AI) agents, powered by Large Language Models (LLMs), advance rapidly toward interconnected systems -- an Internet of Agents (IoA). This vision enables complex problem-solving while introducing systemic…
With the growing realization that current Internet protocols are reaching the limits of their senescence, a number of on-going research efforts aim to design potential next-generation Internet architectures. Although they vary in maturity…
The absence of a fully decentralized, verifiable, and privacy-preserving communication protocol for autonomous agents remains a core challenge in decentralized computing. Existing systems often rely on centralized intermediaries, which…
The proliferation of autonomous AI agents marks a paradigm shift toward complex, emergent multi-agent systems. This transition introduces systemic security risks, including control-flow hijacking and cascading failures, that traditional…
The rapid development of the AI agent communication protocols, including the Model Context Protocol (MCP), Agent2Agent (A2A), Agora, and Agent Network Protocol (ANP), is reshaping how AI agents communicate with tools, services, and each…
In the artificial intelligence space, as we transition from isolated large language models to autonomous agents capable of complex reasoning and tool use. While foundational architectures and local context management protocols have been…
The absence of security and privacy measures between DNS recursive resolvers and authoritative nameservers has been exploited by both on-path and off-path attackers. Although numerous security proposals have been introduced in practice and…
With the rise of large language and vision-language models, AI agents have evolved into autonomous, interactive systems capable of perception, reasoning, and decision-making. As they proliferate across virtual and physical domains, the…
During disasters, crisis, and emergencies the public relies on online services provided by official authorities to receive timely alerts, trustworthy information, and access to relief programs. It is therefore crucial for the authorities to…
LLM-based agents are rapidly proliferating, yet the infrastructure for discovering, evaluating, and governing them remains fragmented compared to mature ecosystems like software package registries (e.g., npm) and model hubs (e.g., Hugging…
Large language models (LLMs) and retrieval-augmented generation (RAG) techniques have revolutionized traditional information access, enabling AI agent to search and summarize information on behalf of users during dynamic dialogues. Despite…
As AI systems gain increasing autonomy and execution capability, the number of discovered security vulnerabilities continues to rise. However, many of these vulnerabilities are not fundamentally novel, but instead reflect recurring classes…
Recent surges in LLM-driven intelligent systems largely overlook decades of foundational multi-agent systems (MAS) research, resulting in frameworks with critical limitations such as centralization and inadequate trust and communication…
Given the rise in cyber threats to networked systems, coupled with the proliferation of AI techniques and enhanced processing capabilities, Denial of Service (DoS) attacks are becoming increasingly sophisticated and easily executable. They…