Related papers: Toward a Safe Internet of Agents
The rapid rise of autonomous AI systems and advancements in agent capabilities are introducing new risks due to reduced oversight of real-world interactions. Yet agent testing remains nascent and is still a developing science. As AI agents…
Agentic AI marks an important transition from single-step generative models to systems capable of reasoning, planning, acting, and adapting over long-lasting tasks. By integrating memory, tool use, and iterative decision cycles, these…
Autonomous AI agents powered by large language models are being deployed in production with capabilities including shell execution, file system access, database queries, and multi-party communication. Recent red teaming research…
AI agent frameworks connecting large language model (LLM) reasoning to host execution surfaces -- shell, filesystem, containers, and messaging -- introduce security challenges structurally distinct from conventional software. We present a…
The rapid evolution of Large Language Models (LLMs) into autonomous, tool-calling agents has fundamentally altered the cybersecurity landscape. Frameworks like OpenClaw grant AI systems operating-system-level permissions and the autonomy to…
Recent advances in AI are transforming AI's ubiquitous presence in our world from that of standalone AI-applications into deeply integrated AI-agents. These changes have been driven by agents' increasing capability to autonomously make…
The emergence of Large Language Models (LLMs) has significantly advanced solutions across various domains, from political science to software development. However, these models are constrained by their training data, which is static and…
This paper presents a Unified Security Architecture that fortifies the Agentic Web through a Zero-Trust IAM framework. This architecture is built on a foundation of rich, verifiable agent identities using Decentralized Identifiers (DIDs)…
The endowment of AI with reasoning capabilities and some degree of agency is widely viewed as a path toward more capable and generalizable systems. Our position is that the current development of agentic AI requires a more holistic,…
In this work we present the first holistic survey of the agentic security landscape, structuring the field around three fundamental pillars: Applications, Threats, and Defenses. We provide a comprehensive taxonomy of over 160 papers,…
Large language models (LLMs) deployed as agents introduce significant safety risks in clinical settings due to their potential for error and single points of failure. We introduce Tiered Agentic Oversight (TAO), a hierarchical multi-agent…
Large Language Models (LLMs) are accelerating the shift from an Internet of information to an Internet of Agents (IoA), where autonomous entities discover services, negotiate, execute tasks, and exchange value. Yet today's agents are still…
The concept of the 'agent' has profoundly shaped Artificial Intelligence (AI) research, guiding development from foundational theories to contemporary applications like Large Language Model (LLM)-based systems. This paper critically…
The concept of autonomy is key to the IoT vision promising increasing integration of smart services and systems minimizing human intervention. This vision challenges our capability to build complex open trustworthy autonomous systems. We…
Security Operations Centers (SOCs) increasingly encounter difficulties in correlating heterogeneous alerts, interpreting multi-stage attack progressions, and selecting safe and effective response actions. This study introduces AgentSOC, a…
Traditional Identity and Access Management (IAM) systems, primarily designed for human users or static machine identities via protocols such as OAuth, OpenID Connect (OIDC), and SAML, prove fundamentally inadequate for the dynamic,…
Autonomous AI agents powered by large language models (LLMs) with structured function-calling interfaces enable real-time data retrieval, computation, and multi-step orchestration. However, the rapid growth of plugins, connectors, and…
The rapid development of large language models (LLMs) has led to the widespread deployment of LLM agents across diverse industries, including customer service, content generation, data analysis, and even healthcare. However, as more LLM…
LLM-based multi-agent systems have demonstrated impressive capabilities, but they also introduce significant safety risks when individual agents fail or behave adversarially. In this work, we study the automated design of agentic systems…
AI systems have found a wide range of real-world applications in recent years. The adoption of edge artificial intelligence, embedding AI directly into edge devices, is rapidly growing. Despite the implementation of guardrails and safety…