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. From Attack Surface to Defense Architecture: Compositional Security for Agentic Coding Harnesses

    Nov 10, 2026Simon Hegelich, Bardh Prenkaj, Habiba Sarhan +5AI Agent SecurityTool Access Control for LLM Agents

  2. No finite rulebook can certify every safe program: an impossibility theorem for gatekeeping AI agents

    Nov 9, 2026Tomas Perez-AcleAI Agent SafetyFormal Verification

  3. The Limits of Information-Flow Control Enforcement for Agentic Systems

    Nov 7, 2026Jonathan Gregory, Kyle Domico, Kunyang Li +2Information Flow ControlAI Agent Security

  4. Secure Formal Raising: Protecting the Development of AI through Executable Properties

    Nov 5, 2026Rolf Drechsler, Christina PlumpAI AssuranceFormal Verification

  5. Signed, Sealed, Leaked: Trust Beyond Signature for MCP Toolchains

    Nov 4, 2026Yichiet Aun, Mohammed A. Alhartomi, Jing Jie Tan +4AI Agent SecurityMCP Security

  6. Judging Before Propagation: Task-Graph Contextual Integrity for Multi-Agent Privacy

    Oct 29, 2026Hengyu Wu, Blaise Delattre, Yang CaoPrivacy Protection for LLM AgentsContextual Integrity

  7. SPIDES: Information-Flow Control for Browser Agents

    Oct 16, 2026Egor Zverev, Juhee Kim, Leon Trampert +4LLM Agent SecurityInformation Flow Control

  8. CascadeLedger: Counterfactual Auditing of Information and Resource Integrity in LLM Cascades

    Oct 14, 2026Miaobo Hu, Shuhao Hu, Xiaobo Guo +3Language Model CascadingLLM Auditing

  9. Can CaMeLs Talk? Securing Multi-Agent Systems Against Indirect Prompt Injection Attacks

    Oct 5, 2026James Peters-Gill, Avi Semler, Henning Bartsch +2AI Agent Security BenchmarksInformation Flow Control

  10. G-CARB: Graph-Localized Conformal Agent Risk Budget for Compositional Harm

    Oct 4, 2026Zijun Yu, Yu Gu, Vahid Partovi Nia +1AI Agent SafetyConformal Risk Control

  11. Deny Without Disabling: Authorization-Paired Evaluation and Control for Multi-Agent Systems

    Sep 30, 2026Yunbei Zhang, Saiyue Lyu, Janet Wang +4Multi-Agent CollaborationInformation Flow Control

  12. AkasicMEM: Governed Enterprise Memory for Agents

    Sep 22, 2026Jeongmin Bae, Yongjae Kim, Kyoung Hur +2Agent MemoryAgent Memory Governance

  13. Environment Steering: Using Data Flow Control to Improve Agent Utility and Safety

    Sep 19, 2026Charlie Summers, Prajwal Raghunath, Aaditya Pai +4AI Agent SecurityLLM Agent Safety

  14. Confuse the Model, Control the Flow: Understanding and Mitigating Privacy Leakage from LLM Agents with Information Flow Control

    Sep 12, 2026Minsun Shim, Ramisha Raida Karim, Ruthwik Jakkula +4LLM Agent SecurityPrivacy Leakage in Language Models

  15. Reachability-Based Capability Confinement for LLM Agents under Indirect Prompt Injection

    Aug 30, 2026Wujie Xiong, Rabimba Karanjai, Yang Lu +2LLM Agent SecurityInformation Flow Control

  16. MNC: Scope-Bound Semantic Declassification for Private LLM-Agent Communication

    Aug 3, 2026Jinghan Xu, Longze Fan, Zeyuan Wang +2Multi-Agent LLM SystemsLLM Agent Security

  17. SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems

    Jul 28, 2026Haowen Dai, Zonghao Ying, Wenfeng Li +10AI Agent SafetyInformation Flow Control

  18. Coordinated Networking for On-Device Agent-Augmented Real-Time Communication

    Jul 24, 2026Goodsol Lee, Juheon Yi, Jinglu Wang +3Information Flow Control

  19. Prismata: Confining Cross-Site Prompt Injection in Web Agents

    Jul 9, 2026Corban Villa, Alp Eren Ozdarendeli, Sijun Tan +1LLM Agent SecurityInformation Flow Control

  20. Securing Multi-Tool AI Agent Chains With Dynamic, Real-Time Compositional Policies

    Jul 3, 2026Chris Schneider, Kriti Faujdar, Philipp Schoenegger +1LLM Agent SecurityInformation Flow Control

  21. Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents

    Jun 25, 2026Nada Lahjouji, Ashwin Gerard ColacoPrivacy Leakage in Language ModelsInformation Flow Control

  22. AOHP: An Open-Source OS-Level Agent Harness for Personalized, Efficient and Secure Interaction

    Jun 22, 2026Shanhui Zhao, Jiacheng Liu, Guohong Liu +13Computer-Use AgentsAI Agent Security

  23. GIF: Locally Sound Geometric Information Flow Control for LLMs

    Jun 22, 2026Adam Storek, Nikolaus Holzer, Zhuo Zhang +1Privacy Leakage in Language ModelsLLM Security

  24. Data Flow Control: Data Safety Policies for AI Agents

    Jun 4, 2026Charlie Summers, Eugene WuAI Agent SecurityInformation Flow Control

  25. Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control

    May 26, 2026Zhe Yu, Wenpeng Xing, Gaolei Li +4RAG Poisoning AttacksInformation Flow Control

  26. Language-Based Agent Control

    May 13, 2026Timothy Zhou, Loris D'Antoni, Nadia PolikarpovaAI Agent SecurityInformation Flow Control