fides

Protegiendo Agentes de IA con Control de Flujo de Información Este repositorio contiene un cuaderno de Jupyter que acompaña al artículo académico «Protegiendo agentes de IA con control de flujo de información». El cuaderno está estructurado como un tutorial para guiar a los lectores a través de l...

Optimizing Agent Planning for Security and Autonomy

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, but currently appear costly: they reduce task completion...

Securing AI Agents with Information-Flow Control

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 t...

AIs as Trusted Third Parties

This is a truly fascinating paper: "Trusted Machine Learning Models Unlock Private Inference for Problems Currently Infeasible with Cryptography." The basic idea is that AIs can act as trusted third parties: Abstract: We often interact with untrusted parties. Prioritization of privacy can limit t...