Related papers: AgentGuard: Runtime Verification of AI Agents
The rise of Agent AI and Large Language Model-powered Multi-Agent Systems (LLM-MAS) has underscored the need for responsible and dependable system operation. Tools like LangChain and Retrieval-Augmented Generation have expanded LLM…
As generative AI (GenAI) agents become more common in enterprise settings, they introduce security challenges that differ significantly from those posed by traditional systems. These agents are not just LLMs; they reason, remember, and act,…
We present the Agentic AI Detection and Response (ADR) system, the first large-scale, production-proven enterprise framework for securing AI agents operating through the Model Context Protocol (MCP). We identify three persistent challenges…
Designing realistic and adaptive networked threat scenarios remains a core challenge in cybersecurity research and training, still requiring substantial manual effort. While large language models (LLMs) show promise for automated synthesis,…
Agentic AI shifts the investor's role from analytical execution to oversight. We present an agentic strategic asset allocation pipeline in which approximately 50 specialized agents produce capital market assumptions, construct portfolios…
Autonomous UI agents powered by AI have tremendous potential to boost human productivity by automating routine tasks such as filing taxes and paying bills. However, a major challenge in unlocking their full potential is security, which is…
The proliferation of open-source software (OSS) has made software supply chains prime targets for attacks like Package Confusion, where adversaries publish malicious packages with names deceptively similar to legitimate ones. To protect…
The deployment of autonomous systems that operate in unstructured environments necessitates algorithms to verify their safety. This can be challenging due to, e.g., black-box components in the control software, or undermodelled dynamics…
To enable human oversight, agentic AI systems often provide a trace of reasoning and action steps. Designing traces to have an informative, but not overwhelming, level of detail remains a critical challenge. In three user studies on a…
Indirect prompt injection attacks threaten AI agents that execute consequential actions, motivating deterministic system-level defenses. Such defenses can provably block unsafe actions by enforcing confidentiality and integrity policies,…
The development of artificial intelligence systems is transitioning from creating static, task-specific models to dynamic, agent-based systems capable of performing well in a wide range of applications. We propose an Interactive Agent…
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…
The autonomous AI agents using large language models can create undeniable values in all span of the society but they face security threats from adversaries that warrants immediate protective solutions because trust and safety issues arise.…
Traditional network experiments focus on validation through either simulation or emulation. Each approach has its own advantages and limitations. In this work, we present a new tool for next-generation network experiments created through…
Conventional algorithmic trading systems are grounded in deterministic heuristics or offline-trained statistical models that cannot adapt to the semantic complexity of rapidly shifting market regimes. This paper introduces AGENTICAITA, an…
Multi-agent reinforcement learning (RL) often struggles to ensure the safe behaviours of the learning agents, and therefore it is generally not adapted to safety-critical applications. To address this issue, we present a methodology that…
Agentic AI systems are increasingly capable of performing professional and personal tasks with limited human involvement. However, tracking these developments is difficult because the AI agent ecosystem is complex, rapidly evolving, and…
Our paper introduces a generative, multiagent AI framework designed to overcome the rigidity, limited flexibility and technical barriers of current bibliometric tools. The objective is to enable researchers to perform fully dynamic,…
Agentic AI represents a paradigm shift in enhancing the capabilities of generative AI models. While these systems demonstrate immense potential and power, current evaluation techniques primarily focus on assessing their efficacy in…
Agentic systems for business process automation often require compliance with policies governing conditional updates to the system state. Evaluation of policy adherence in LLM-based agentic workflows is typically performed by comparing the…