Overview

Information flow control studies how to prevent sensitive or untrusted data from reaching unauthorized destinations or influencing unsafe actions. Systems label data and track its provenance using techniques such as taint analysis, security lattices, capabilities, and type systems, then enforce rules with runtime monitors or policy-aware data infrastructure. For AI agents, these controls can cover tool use, prompt-injection risks, retrieval, persistent memory, and communication between agents, with carefully scoped declassification allowing permitted disclosures. A central challenge is maintaining strong, compositional guarantees across changing workflows and recipients without blocking useful work; benchmarks and formal methods are still catching up with these complex settings.

Latest papers

CardsList

34 papers7 papers in the last four weeks, up 17% on the four weeks before. 0.0% of all new papers.

  1. The Granularity Mismatch in Agent Security: Argument-Level Provenance Solves Enforcement and Isolates the LLM Reasoning Bottleneck

    May 11, 2026Linfeng Fan, Ziwei Li, Yuan Tian +3LLM Agent SecurityInformation Flow Control

  2. An AI Agent Execution Environment to Safeguard User Data

    Apr 21, 2026Robert Stanley, Avi Verma, Lillian Tsai +2AI Agent SecurityPrivacy Leakage in Language Models

  3. Free Information Disrupts Even Bayesian Crowds

    Apr 2, 2026Jonas Stein, Shannon Cruz, Davide Grossi +1Information Flow ControlOpinion Dynamics

  4. Tracking Capabilities for Safer Agents

    Mar 1, 2026Martin Odersky, Yaoyu Zhao, Yichen Xu +2AI Agent SafetyTool Access Control for LLM Agents