Related papers: A2AS: Agentic AI Runtime Security and Self-Defense
Large Language Model (LLM) agents can leverage tools such as Google Search to complete complex tasks. However, this tool usage introduces the risk of indirect prompt injections, where malicious instructions hidden in tool outputs can…
The rise of Large Language Model (LLM) agents, augmented with tool use, skills, and external knowledge, has introduced new security risks. Among them, prompt injection attacks, where adversaries embed malicious instructions into the agent…
Agentic AI systems present both significant opportunities and novel risks due to their capacity for autonomous action, encompassing tasks such as code execution, internet interaction, and file modification. This poses considerable…
Indirect prompt injection threatens LLM agents by embedding malicious instructions in external content, enabling unauthorized actions and data theft. LLM agents maintain working memory through their context window, which stores interaction…
As AI agents become increasingly autonomous and capable, ensuring their security against vulnerabilities such as prompt injection becomes critical. This paper explores the use of information-flow control (IFC) to provide security guarantees…
Uganda's rapid digital transformation, supported by national strategies such as Vision 2040 and the Digital Transformation Roadmap, has expanded reliance on networked services while simultaneously increasing exposure to sophisticated cyber…
Autonomous AI agents that can follow instructions and perform complex multi-step tasks have tremendous potential to boost human productivity. However, to perform many of these tasks, the agents need access to personal information from their…
As Large Language Models (LLMs) continue to be increasingly applied across various domains, their widespread adoption necessitates rigorous monitoring to prevent unintended negative consequences and ensure robustness. Furthermore, LLMs must…
We present Agent S, an open agentic framework that enables autonomous interaction with computers through a Graphical User Interface (GUI), aimed at transforming human-computer interaction by automating complex, multi-step tasks. Agent S…
We undertake a comprehensive and structured synthesis of the drivers of human behavior in cybersecurity, focusing specifically on people within organizations (i.e., especially employees in companies), and integrate key concepts such as…
Backdoor attacks pose a serious threat to the secure deployment of large language models (LLMs), enabling adversaries to implant hidden behaviors triggered by specific inputs. However, existing methods often rely on manually crafted…
The rapid evolution of sophisticated cyberattacks has strained modern Security Operations Centers (SOC), which traditionally rely on rule-based or signature-driven detection systems. These legacy frameworks often generate high volumes of…
Agentic AI systems capable of reasoning, planning, and executing actions present fundamentally distinct governance challenges compared to traditional AI models. Unlike conventional AI, these systems exhibit emergent and unexpected behaviors…
Recent advances in agentic AI have enabled increasingly autonomous workflows, but existing systems still face substantial challenges in achieving reliable deployment in real-world scientific research. In this work, we present a safe,…
Large Language Model (LLM) applications are vulnerable to prompt injection and context manipulation attacks that traditional security models cannot prevent. We introduce two novel primitives--authenticated prompts and authenticated…
AI agents are beginning to interact with each other directly and across internet platforms and physical environments, creating security challenges beyond traditional cybersecurity and AI safety frameworks. Free-form protocols are essential…
As Artificial Intelligence (AI) systems proliferate, the need for systematic, transparent, and actionable processes for evaluating them is growing. While many resources exist to support AI evaluation, they have several limitations. Few…
Large Language Models (LLMs) have been increasingly integrated into computer-use agents, which can autonomously operate tools on a user's computer to accomplish complex tasks. However, due to the inherently unstable and unpredictable nature…
The rise of large model-based AI agents has spurred interest in Multi-Agent Systems (MAS) for their capabilities in decision-making, collaboration, and adaptability. While the Model Context Protocol (MCP) addresses tool invocation and data…
We propose a foundational runtime actuarial layer for autonomous AI agents in which every side-effect-bearing action carries a time-consistent, counterfactual risk toll computed against a contractually fixed safe default, inside an explicit…