paper-with-me

홈 › Papers

Securing AI Agents with Information-Flow Control

2025-05-29 · Manuel Costa, Boris Köpf, Aashish Kolluri, Andrew Paverd, Mark Russinovich, Ahmed Salem, Shruti Tople, Lukas Wutschitz, Santiago Zanella-Béguelin

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 for AI agents. We present a formal model to reason about the security and expressiveness of agent planners. Using this model, we characterize the class of properties enforceable by dynamic taint-tracking and construct a taxonomy of tasks to evaluate security and utility trade-offs of planner designs. Informed by this exploration, we present Fides, a planner that tracks confidentiality and integrity labels, deterministically enforces security policies, and introduces novel primitives for selectively hiding information. Its evaluation in AgentDojo demonstrates that this approach broadens the range of tasks that can be securely accomplished. A tutorial to walk readers through the the concepts introduced in the paper can be found at https://github.com/microsoft/fides

📄 PDF Abstract BibTeX arXiv:2505.23643

Code (1)

microsoft/fides 공식 구현

Similar Papers 제목 키워드 기반

Defeating Prompt Injections by Design

2025-03-24 · Edoardo Debenedetti, Ilia Shumailov, Tianqi Fan, Jamie Hayes 외

Large Language Models (LLMs) are increasingly deployed in agentic systems that interact with an untrusted environment. However, LLM agents are vulnerable to prompt injection attacks when handling untrusted data. In this …

AgentBound: Securing Execution Boundaries of AI Agents

2025-10-24 · Christoph Bühler, Matteo Biagiola, Luca Di Grazia, Guido Salvaneschi arxiv

Large Language Models (LLMs) have evolved into AI agents that interact with external tools and environments to perform complex tasks. The Model Context Protocol (MCP) has become the de facto standard for connecting agent…

Causality Laundering: Denial-Feedback Leakage in Tool-Calling LLM Agents

2026-04-05 · Mohammad Hossein Chinaei arxiv

Tool-calling LLM agents can read private data, invoke external services, and trigger real-world actions, creating a security problem at the point of tool execution. We identify a denial-feedback leakage pattern, which we…

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

2026-04-25 · Tianlong Yu, Yang Yang, Xiao Luo, Lihong Liu 외 arxiv

Emerging AR-LLM-based Social Engineering attack (e.g., SEAR) is at the edge of posing great threats to real-world social life. In such AR-LLM-SE attack, the attacker can leverage AR (Augmented Reality) glass to capture t…

Securing AI Agents: Implementing Role-Based Access Control for Industrial Applications

2025-09-14 · Aadil Gani Ganie arxiv

The emergence of Large Language Models (LLMs) has significantly advanced solutions across various domains, from political science to software development. However, these models are constrained by their training data, whi…