A Safety and Security Framework for Real-World Agentic Systems

• URL: http://arxiv.org/abs/2511.21990v1
• Date: Thu, 27 Nov 2025 00:19:24 GMT
• Title: A Safety and Security Framework for Real-World Agentic Systems
• Authors: Shaona Ghosh, Barnaby Simkin, Kyriacos Shiarlis, Soumili Nandi, Dan Zhao, Matthew Fiedler, Julia Bazinska, Nikki Pope, Roopa Prabhu, Daniel Rohrer, Michael Demoret, Bartley Richardson,
• Abstract summary: This paper introduces a dynamic and actionable framework for securing agentic AI systems in enterprise deployment.<n>We propose a new way of identification of novel agentic risks through the lens of user safety.<n>We demonstrate the framework effectiveness through a detailed case study of NVIDIA flagship agentic research assistant, AI-Q Research Assistant.
• Score: 2.05255620498371
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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 from the dynamic interactions among models, orchestrators, tools, and data within their operating environments. We propose a new way of identification of novel agentic risks through the lens of user safety. Although, for traditional LLMs and agentic models in isolation, safety and security has a clear separation, through the lens of safety in agentic systems, they appear to be connected. Building on this foundation, we define an operational agentic risk taxonomy that unifies traditional safety and security concerns with novel, uniquely agentic risks, including tool misuse, cascading action chains, and unintended control amplification among others. At the core of our approach is a dynamic agentic safety and security framework that operationalizes contextual agentic risk management by using auxiliary AI models and agents, with human oversight, to assist in contextual risk discovery, evaluation, and mitigation. We further address one of the most challenging aspects of safety and security of agentic systems: risk discovery through sandboxed, AI-driven red teaming. We demonstrate the framework effectiveness through a detailed case study of NVIDIA flagship agentic research assistant, AI-Q Research Assistant, showcasing practical, end-to-end safety and security evaluations in complex, enterprise-grade agentic workflows. This risk discovery phase finds novel agentic risks that are then contextually mitigated. We also release the dataset from our case study, containing traces of over 10,000 realistic attack and defense executions of the agentic workflow to help advance research in agentic safety.

Related papers

• SafePro: Evaluating the Safety of Professional-Level AI Agents [29.90240552544994]
  Large language model-based agents are rapidly evolving from simple conversational assistants into autonomous systems capable of performing complex, professional-level tasks.<n>Existing safety evaluations primarily focus on simple, daily assistance tasks, failing to capture the intricate decision-making processes and potential consequences of misaligned behaviors in professional settings.<n>We introduce SafePro, a benchmark designed to evaluate the safety alignment of AI agents performing professional activities.
  arXiv  Detail & Related papers  (2026-01-10T19:53:09Z)
• SafeMobile: Chain-level Jailbreak Detection and Automated Evaluation for Multimodal Mobile Agents [58.21223208538351]
  This work explores the security issues surrounding mobile multimodal agents.<n>It attempts to construct a risk discrimination mechanism by incorporating behavioral sequence information.<n>It also designs an automated assisted assessment scheme based on a large language model.
  arXiv  Detail & Related papers  (2025-07-01T15:10:00Z)
• Kaleidoscopic Teaming in Multi Agent Simulations [75.47388708240042]
  We argue that existing red teaming or safety evaluation frameworks fall short in evaluating safety risks in complex behaviors, thought processes and actions taken by agents.<n>We introduce new in-context optimization techniques that can be used in our kaleidoscopic teaming framework to generate better scenarios for safety analysis.<n>We present appropriate metrics that can be used along with our framework to measure safety of agents.
  arXiv  Detail & Related papers  (2025-06-20T23:37:17Z)
• Securing Generative AI Agentic Workflows: Risks, Mitigation, and a Proposed Firewall Architecture [0.0]
  Generative Artificial Intelligence (GenAI) presents significant advancements but also introduces novel security challenges.<n>This paper outlines critical security vulnerabilities inherent in GenAI agentic, including data privacy, model manipulation, and issues related to agent autonomy and system integration.<n>It details a proposed "GenAI Security Firewall" architecture designed to provide comprehensive, adaptable, and efficient protection for these systems.
  arXiv  Detail & Related papers  (2025-06-10T07:36:54Z)
• SafeAgent: Safeguarding LLM Agents via an Automated Risk Simulator [77.86600052899156]
  Large Language Model (LLM)-based agents are increasingly deployed in real-world applications.<n>We propose AutoSafe, the first framework that systematically enhances agent safety through fully automated synthetic data generation.<n>We show that AutoSafe boosts safety scores by 45% on average and achieves a 28.91% improvement on real-world tasks.
  arXiv  Detail & Related papers  (2025-05-23T10:56:06Z)
• Securing Agentic AI: A Comprehensive Threat Model and Mitigation Framework for Generative AI Agents [0.0]
  This paper introduces a comprehensive threat model tailored specifically for GenAI agents.<n>Research work identifies 9 primary threats and organizes them across five key domains.
  arXiv  Detail & Related papers  (2025-04-28T16:29:24Z)
• AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection [47.83354878065321]
  We propose AGrail, a lifelong guardrail to enhance agent safety.<n>AGrail features adaptive safety check generation, effective safety check optimization, and tool compatibility and flexibility.
  arXiv  Detail & Related papers  (2025-02-17T05:12:33Z)
• HAICOSYSTEM: An Ecosystem for Sandboxing Safety Risks in Human-AI Interactions [95.49509269498367]
  We present HAICOSYSTEM, a framework examining AI agent safety within diverse and complex social interactions.<n>We run 1840 simulations based on 92 scenarios across seven domains (e.g., healthcare, finance, education)<n>Our experiments show that state-of-the-art LLMs, both proprietary and open-sourced, exhibit safety risks in over 50% cases.
  arXiv  Detail & Related papers  (2024-09-24T19:47:21Z)
• Safeguarding AI Agents: Developing and Analyzing Safety Architectures [0.0]
  This paper addresses the need for safety measures in AI systems that collaborate with human teams.<n>We propose and evaluate three frameworks to enhance safety protocols in AI agent systems.<n>We conclude that these frameworks can significantly strengthen the safety and security of AI agent systems.
  arXiv  Detail & Related papers  (2024-09-03T10:14:51Z)
• EARBench: Towards Evaluating Physical Risk Awareness for Task Planning of Foundation Model-based Embodied AI Agents [53.717918131568936]
  Embodied artificial intelligence (EAI) integrates advanced AI models into physical entities for real-world interaction.<n>Foundation models as the "brain" of EAI agents for high-level task planning have shown promising results.<n>However, the deployment of these agents in physical environments presents significant safety challenges.<n>This study introduces EARBench, a novel framework for automated physical risk assessment in EAI scenarios.
  arXiv  Detail & Related papers  (2024-08-08T13:19:37Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.