Information-Flow Control

Follow this topic Ask about this topic

Momentum

3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 35

All topics

Concealing LLM-Based Multi-Agent Topology via Phantom Structure Injection
Sep 29, 2026Longzhu He, Zelang Wen, Xinfeng Li +2Information-Flow Control Topology
Nanyang Technological University · Beijing University of Posts and Telecommunications · The Hong Kong Polytechnic University
FlowAtom: Atom-Based Evidence Aggregation for Multi-Label Website Fingerprinting
Sep 24, 2026Chongru Fan, Wentao Huang, Wei Wang +4Network Traffic Fingerprint
School of Cyberspace Security, Beijing University of Posts and Telecommunications, Beijing, China · Zhongguancun Laboratory, Beijing, China
Why Does Misinformation Propagate Faster? An Algorithmic Perspective on X
Sep 24, 2026Pan Li, Shuang GaoMisinformation Social Media
Arizona State University
Role differentiation as ignition of a collective information engine: Structuration in Agent Populations
Sep 12, 2026Maximilian Puelma TouzelCollective Behaviors Strategic Agents
Mila–Quebec AI Institute, 6666 St. Urbain Ave., Montreal, Quebec, Canada
Assuming You Knew: Fixing an Epistemic Semantics for Flow Policies Using Agentic AI
Aug 1, 2026David A. NaumannEpistemic State Replication Information-Flow Control
Stevens Institute of Technology, USA
AgentGFM: A Graph Foundation Model with Node-Agent Information-Flow Control
Jul 29, 2026Jingbo Cui, Jitao Zhao, Di Jin +1Graph Foundation Model Information-Flow Control
School of Computer Science and Technology, Tianjin University Tianjin, China
SafeFlow: Semantic Information-Flow Control for Blocking Malicious Propagation in Multi-Agent Systems
Jul 28, 2026Haowen Dai, Zonghao Ying, Wenfeng Li +10Information-Flow Control Malicious Agents
University of Nottingham Ningbo China · Beihang University · Shandong University +6
Agentic Permissions Policy Algebra for Taint Confinement in LLM Agents
Jul 27, 2026Arseny Kravchenko, Vadim Liventsev, Innokentii Konstantinov +2Realistic Threat Model Information-Flow Control
Archestra AI
Structured Fluctuations and the Information Dynamics of Self-Maintenance in Growing Neural Cellular Automata
Jul 14, 2026Atsushi Masumori, Hiroki Sato, Takashi IkegamiNeural Cellular Automata Self-Repair
The University of Tokyo · Atomi University · Alternative Machine Inc.
MPFlow: Learning Budgeted Max-Flow Optimization on the Lightning Network with Deep Graph Reinforcement Learning
Jul 9, 2026Harrison Rush, Vincent Davis, Simone Antonelli +3Bringing Network Coding Flow Policies
Amboss Technologies, Green Cove Springs, USA · CISPA Helmholtz Center for Information Security · Stillmark, San Francisco, USA +1
Information Dynamics of Language Communication
Jun 29, 2026Leonardo S. Goodall, Andrea I. Luppi, Pedro A. M. MedianoInformation-Flow Control Semantic Entropy
Calleva Research Centre, University of Oxford, UK · St John’s College, University of Cambridge, UK · Montr´eal Neurological Institute, McGill University, Canada +2
ToolPrivacyBench: Benchmarking Purpose-Bound Privacy in Tool-Using LLM Agents
Jun 26, 2026Shijing Hu, Liang Liu, Zhu Meng +1Language-Model Agents Privacy
Beijing University of Posts and Telecommunications, Beijing, 100876, China · Beijing Academy of Blockchain and Edge Computing, Beijing, 100085, China
Explaining Temporal Graph Neural Networks via Feature-induced Information Flow
Jun 25, 2026Ping Xiong, Thomas Schnake, Klaus-Robert Müller +1Temporal Graph Neural Networks Information-Flow Control
Berlin Institute for the Foundations of Learning and Data – BIFOLD, 10623 Berlin, Germany · Machine Learning Group, Technical University of Berlin, Berlin, Germany · Department of Chemistry, Chemical Physics Theory Group, University of Toronto, Toronto, Canada +5
Agents That Know Too Much: A Data-Centric Survey of Privacy in LLM Agents
Jun 25, 2026Nada Lahjouji, Ashwin Gerard ColacoPrivacy Large Language Model Agents
University of California, Irvine Irvine, California, USA
Infinitesimal Causality
Jun 23, 2026Sridhar MahadevanInformation-Flow Control Tangent Space
Adobe Research and University of Massachusetts, Amherst
GIF: Locally Sound Geometric Information Flow Control for LLMs
Jun 22, 2026Adam Storek, Nikolaus Holzer, Zhuo Zhang +1Information-Flow Control Data Leakage
Columbia University
Mesh Inference: A Formal Model of Collective Inference Without a Center
Jun 17, 2026Hongwei XuProbabilistic Inference Information-Flow Control
DIPHINE: Diffusion-based $Φ$ -ID Neural Estimator
Jun 17, 2026Simon Pedro Galeano Munoz, Mustapha Bounoua, Giulio Franzese +2Inference Dynamics Information-Flow Control
KAUST, Saudi Arabia · EURECOM, France
AI Contagion in Social Networks
Jun 13, 2026Olivier Bos, Stefano BosiSocial Media Information-Flow Control
Université Paris-Saclay, ENS Paris-Saclay, Centre for Economics at Paris-Saclay. · Université Paris-Saclay, Université d’Evry Paris-Saclay, Centre for Economics at Paris-Saclay, EPEE.
How Does Reasoning Flow? Tracing Attention-Induced Information Flow for Targeted RL in LLMs
Jun 9, 2026Zhichen Dong, Yang Li, Yuhan Sun +9Large Language Model Reinforcement Learning LLM Reasoning Strategies
1Shanghai Jiao Tong University · 2Alibaba Group · 3Shanghai Artificial Intelligence Laboratory
Hasse Diagrams for Attention: A Partial Order Framework for Designing Transformer Masks
Jun 8, 2026Chentao Li, Han GuoTransformer Attention Mask2Former
School of Mathematics and Statistics Northeast Petroleum University Daqing, Heilongjiang 163318, China
Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
May 26, 2026Zhe Yu, Wenpeng Xing, Gaolei Li +4Poisoning Information-Flow Control
Binjiang Institute of Zhejiang University · Zhejiang University · Shanghai Jiao Tong University +3
GL-LFGNN:A Global-Local Dual-branch Causal Graph Neural Network Based on Liang-Kleeman Information Flow for EEG Emotion Recognition
May 24, 2026Ziyi Wang, Dongyang KuangElectroencephalography Human Brain Networks
Faithfulness as Information Flow: Evaluating and Training Faithful Chain-of-Thought Reasoning
May 22, 2026Jinghan Jia, Joe Benton, Eric EasleyExplanation Faithfulness Faithfulness
†Dept. CSE, Michigan State University · ⋆Anthropic Fellows Program · ‡Anthropic
A Multi-Layer AI Framework for Information Landscape Analysis
May 22, 2026Maryam Fooladi, Federico BottinoMisinformation Detection Ai-Based Framework
Kakashi Ventures Accelerator (KVA) / Newjee
Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models
May 14, 2026Po-Chien Luan, Wuyang Li, Yang Gao +1Trajectory Forecasting State Space Models
EPFL, Switzerland
Hierarchical Attacks for Multi-Modal Multi-Agent Reasoning
May 13, 2026Hao Zhou, Tiru Wu, Yan Jiang +3Model-Based Multi-Agent Systems Information-Flow Control
Language-Based Agent Control
May 13, 2026Timothy Zhou, Loris D'Antoni, Nadia PolikarpovaAgentic Control Access Control
What If We Let Forecasting Forget? A Sparse Bottleneck for Cross-Variable Dependencies
May 8, 2026Fan Zhang, Shiming Fan, Hua WangMultivariate Time Series Forecasting Information-Flow Control
Shandong Technology and Business University, Yantai, Shandong, China · Ludong University, Yantai, Shandong, China
Breaking the Communication-Accuracy Trade-off: A Sparsified Information Diffusion Framework for Multi-Agent Collaborative Perception
May 1, 2026Jirong Zha, Chenyu Zhao, Nan Zhou +5Collaborative Perception Trajectory-Aware Hidden-State Analyses
Shenzhen International Graduate School, Tsinghua University, Shenzhen 518055, China · Shenzhen Institute of Artificial Intelligence and Robotics, Shenzhen, China, 518000 · Shenzhen Smart City Technology Development Group, Shenzhen, China, 518000
MCPHunt: An Evaluation Framework for Cross-Boundary Data Propagation in Multi-Server MCP Agents
Apr 30, 2026Haonan Li, Tianjun Sun, Yongqing Wang +1Model Context Protocol Information-Flow Control
Key Laboratory of Intraplate Volcanoes and Earthquakes (China University of Geosciences, Beijing), Ministry of Education, Beijing 100083, China · School of Geophysics and Information Technology, China University of Geosciences, Beijing 100083, China
Dont Stop Early: Scalable Enterprise Deep Research with Controlled Information Flow and Evidence-Aware Termination
Apr 27, 2026Prafulla Kumar Choubey, Kung-Hsiang Huang, Pranav Narayanan Venkit +5Deep Research Software Engineering Decision Support
Salesforce AI Research
Aligning What Vision-Language Models See and Perceive with Adaptive Information Flow
Apr 17, 2026Chengxin Liu, Wonseok Choi, Chenshuang Zhang +1Perception Information-Flow Control
KAIST · POSTECH
Learning Peer Influence Probabilities with Linear Contextual Bandits
Oct 21, 2025Ahmed Sayeed Faruk, Mohammad Shahverdikondori, Elena ZhelevaContextual Bandit Framework Influence Function
University of Illinois Chicago, Chicago, USA · École Polytechnique Fédérale de Lausanne, Switzerland
Information propagation dynamics in Deep Graph Networks
Oct 14, 2024Alessio GravinaInformation-Flow Control Spatiotemporal
University of Pisa Department of Computer Science

Sep 29, 2026, cs.CRJ/K move · Enter open · S save

Concealing LLM-Based Multi-Agent Topology via Phantom Structure Injection

Longzhu He, Zelang Wen, Xinfeng Li, Sen Su+1

Nanyang Technological University · Beijing University of Posts and Telecommunications · The Hong Kong Polytechnic University

Information-Flow Control Topology Adversarial Robustness Reasoning Traces

Open paper AskPDF arXiv

Driven by the rapid advancement of large language models (LLMs), LLM-based multi-agent systems (MAS) have emerged as a powerful paradigm for collaborative reasoning over complex tasks. A key design element of MAS is the communication topology, which governs information flow among agents and often encodes proprietary knowledge about the system architecture. However, recent work has shown that such topologies can be inferred even in black-box settings by exploiting semantic dependencies in observable reasoning traces, posing significant risks of intellectual property leakage and exposure of system vulnerabilities. To address this threat, we propose MIRAGE, a topology-concealment framework that preserves the genuine communication topology for task execution while shaping adversary-facing semantic evidence toward a carefully constructed phantom topology. Specifically, MIRAGE operates in three stages: (1) phantom topology synthesis, (2) semantic edge realization, and (3) protected MAS execution. It constructs a phantom topology structurally distinct from the genuine one, materializes phantom edges as plausible semantic dependencies, and suppresses source-specific cues that could reveal genuine edges absent from the phantom topology. Extensive experiments across three topology optimization frameworks and four benchmark datasets demonstrate that MIRAGE substantially reduces the effectiveness of topology inference attacks while largely preserving the task utility of the protected MAS.

Momentum

Related topics

Latest papers 35