Related papers: SUDP: Secret-Use Delegation Protocol for Agentic S…
Traditional AI reasoning techniques have been used successfully in many domains, including logistics, scheduling and game playing. This paper is part of a project aimed at investigating how such techniques can be extended to coordinate…
Modern cloud and enterprise systems rely on identity-centric authorization, assuming that callers possessing valid credentials are safe to execute commands. The emergence of autonomous AI agents invalidates this assumption: agents can…
Large language models (LLMs) are increasingly integrated into real-time machine learning applications, where safeguarding user privacy is paramount. Traditional differential privacy mechanisms often struggle to balance privacy and accuracy,…
Large language models have paved the way to powerful and flexible AI agents, assisting humans by increasingly integrating into their daily life. This flexibility, potential, and growing adoption demands a holistic and cross-disciplinary…
The integration of external data services (e.g., Model Context Protocol, MCP) has made large language model-based agents increasingly powerful for complex task execution. However, this advancement introduces critical security…
The UDP (User Defined Program) system is a scripting framework for controlling and extending instrumentation software. It has been specially designed for air- and space-borne instruments with flexibility, error control, reuse, automation,…
Agents built on LLMs are increasingly deployed across diverse domains, automating complex decision-making and task execution. However, their autonomy introduces safety risks, including security vulnerabilities, legal violations, and…
Local Differential Privacy (LDP) is popularly used in practice for privacy-preserving data collection. Although existing LDP protocols offer high utility for large user populations (100,000 or more users), they perform poorly in scenarios…
Semantic communication (SemCom) has emerged as a promising paradigm for next-generation networks. However, its typical end-to-end joint source--channel coding (JSCC) architecture also raises serious privacy concerns. To guide future secure…
Our computing ecosystem is being transformed by two emerging paradigms: the increased deployment of agentic AI systems and advancements in quantum computing. With respect to agentic AI systems, one of the most critical problems is creating…
User Datagram Protocol (UDP) is a commonly used protocol for data transmission in small embedded systems. UDP as such is unreliable and packet losses can occur. The achievable data rates can suffer if optimal packet sizes are not used. The…
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…
Traditional password based authentication schemes are mostly considered in single server environments. They are unfitted for the multi-server environments from two aspects. On the one hand, users need to register in each server and to store…
Contemporary software architectures struggle to support autonomous agents whose reasoning is adaptive, probabilistic, and context-dependent, while system integration remains dominated by static interfaces and deterministic contracts. This…
Large Language Model (LLM) agents show considerable promise for automating complex tasks using contextual reasoning; however, interactions involving multiple agents and the system's susceptibility to prompt injection and other forms of…
Large language models increasingly operate as autonomous agents that select and invoke tools from large registries. We identify a critical gap: when unauthorized tools are visible in an agent's context, models select them in adversarial…
In this paper, we present a comprehensive architecture for confidential computing, which we show to be general purpose and quite efficient. It executes the application as is, without any added burden or discipline requirements from the…
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 April 2026 disclosure that a frontier large language model escaped its security sandbox, executed unauthorized actions, and concealed its modifications to version control history demonstrates that agentic AI systems with autonomous tool…
AI agents that autonomously interact with external tools and environments have shown great promise across real-world applications. However, their reliance on external data exposes them to serious indirect prompt injection attacks, where…