Related papers: Fortifying the Agentic Web: A Unified Zero-Trust A…
Agentic AI systems -- Large Language Models (LLMs) augmented with planning, tool use, memory, and long-horizon interactions -- can execute complex tasks autonomously, but their multi-step trajectories introduce new failure modes that…
Agentic AI systems powered by large language models (LLMs) and endowed with planning, tool use, memory, and autonomy, are emerging as powerful, flexible platforms for automation. Their ability to autonomously execute tasks across web,…
The proliferation of AI agents requires robust mechanisms for secure discovery. This paper introduces the Agent Name Service (ANS), a novel architecture based on DNS addressing the lack of a public agent discovery framework. ANS provides a…
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…
Recent progress in (Large) Language Models (LMs) has enabled the development of autonomous LM-based agents capable of executing complex tasks with minimal supervision. These agents have started to be integrated into systems with significant…
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…
AI agents -- powered by reasoning-capable large language models (LLMs) and integrated with tools, data, and web search -- are poised to transform the internet into a \emph{Web of Agents}: a machine-native ecosystem where autonomous agents…
Customer Identity and Access Management (CIAM) systems play a pivotal role in securing enterprise infrastructures. However, the complexity of implementing these systems requires careful architectural planning to ensure positive Return on…
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…
Agentic frameworks are the software layer through which AI agents act in the world. Existing safety methods intervene on the model and therefore remain conditional on unverifiable properties of learned behavior. We introduce containment…
This chapter argues that the reliability of agentic and generative AI is chiefly an architectural property. We define agentic systems as goal-directed, tool-using decision makers operating in closed loops, and show how reliability emerges…
In an era where vast amounts of data are collected and processed from diverse sources, there is a growing demand for sophisticated AI systems capable of intelligently fusing and analyzing this information. To address these challenges,…
The software supply chain attacks are becoming more and more focused on trusted development and delivery procedures, so the conventional post-build integrity mechanisms cannot be used anymore. The available frameworks like SLSA, SBOM and in…
This article, a lightly adapted version of Perplexity's response to NIST/CAISI Request for Information 2025-0035, details our observations and recommendations concerning the security of frontier AI agents. These insights are informed by…
Multi-agent systems (MAS) powered by LLMs promise adaptive, reasoning-driven enterprise workflows, yet granting agents autonomous control over tools, memory, and communication introduces attack surfaces absent from deterministic pipelines.…
Evolving AI systems increasingly deploy multi-agent architectures where autonomous agents collaborate, share information, and delegate tasks through developing protocols. This connectivity, while powerful, introduces novel security risks.…
Autonomous vehicles (AVs) rely on pervasive connectivity to enable cooperative and safety-critical applications, but this connectivity also exposes them to a wide range of cybersecurity threats. Existing perimeter-based security and…
This paper introduces the Identity Control Plane (ICP), an architectural framework for enforcing identity-aware Zero Trust access across human users, workloads, and automation systems. The ICP model unifies SPIFFE-based workload identity,…
Autonomous AI agents lack traceable accountability mechanisms, creating a fundamental dilemma where systems must either operate as ``downgraded tools'' or risk real-world abuse. This vulnerability stems from the limitations of traditional…
European financial institutions face mounting regulatory pressure while their security operations centres remain constrained not by data or staffing but by reasoning capacity: enterprise SIEMs cover only a fraction of MITRE ATT&CK…