From Prompts to Packets: A View from the Network on ChatGPT, Copilot, and Gemini

• URL: http://arxiv.org/abs/2510.11269v1
• Date: Mon, 13 Oct 2025 10:58:54 GMT
• Title: From Prompts to Packets: A View from the Network on ChatGPT, Copilot, and Gemini
• Abstract summary: This study presents an in-depth investigation of traffic generated by three leading chatbots (ChatGPT, Copilot, and Gemini) when accessed via Android mobile apps for both text and image generation.<n>We provide fine-grained traffic characterization at trace, flow, and protocol levels, and model packet-sequence dynamics with Multimodal Markov Chains.<n>Our analyses reveal app- and content-specific traffic patterns, particularly in volume, uplink/downlink profiles, and protocol adoption.
• Score: 4.214795904343115
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Generative AI (GenAI) chatbots are now pervasive in digital ecosystems, yet their network traffic remains largely underexplored. This study presents an in-depth investigation of traffic generated by three leading chatbots (ChatGPT, Copilot, and Gemini) when accessed via Android mobile apps for both text and image generation. Using a dedicated capture architecture, we collect and label two complementary workloads: a 60-hour generic dataset with unconstrained prompts, and a controlled dataset built from identical prompts across GenAI apps and replicated via conventional messaging apps to enable one-to-one comparisons. This dual design allows us to address practical research questions on the distinctiveness of GenAI traffic, its differences from widely deployed traffic categories, and its novel implications for network usage. To this end, we provide fine-grained traffic characterization at trace, flow, and protocol levels, and model packet-sequence dynamics with Multimodal Markov Chains. Our analyses reveal app- and content-specific traffic patterns, particularly in volume, uplink/downlink profiles, and protocol adoption. We highlight the predominance of TLS, with Gemini extensively leveraging QUIC, ChatGPT exclusively using TLS 1.3, and app- and content-specific Server Name Indication (SNI) values. A payload-based occlusion analysis quantifies SNI's contribution to classification: masking it reduces F1-score by up to 20 percentage points in GenAI app traffic classification. Finally, compared with conventional messaging apps when carrying the same content, GenAI chatbots exhibit unique traffic characteristics, highlighting new stress factors for mobile networks, such as sustained upstream activity, with direct implications for network monitoring and management. We publicly release the datasets to support reproducibility and foster extensions to other use cases.

Related papers

• Interactive Tracking: A Human-in-the-Loop Paradigm with Memory-Augmented Adaptation [60.96010213186819]
  We introduce Interactive Tracking, a new paradigm that allows users to guide the tracker at any time using natural language commands.<n>We present InteractTrack, the first large-scale benchmark for interactive tracking, containing 150 videos with dense bounding box annotations and timestamped language instructions.<n>Third, we introduce Interactive Memory-Augmented Tracking (IMAT), a new baseline that employs a dynamic memory mechanism to learn from user feedback and update tracking behavior accordingly.
  arXiv  Detail & Related papers  (2026-04-02T12:33:27Z)
• Generalizable IoT Traffic Representations for Cross-Network Device Identification [15.867734233278568]
  We study the problem of learning generalizable traffic representations for IoT device identification.<n>We design compact encoder architectures that learn per-flow embeddings from unlabeled IoT traffic.<n>We show that these learned representations can be used effectively for IoT device-type classification.
  arXiv  Detail & Related papers  (2026-01-27T07:56:31Z)
• MIETT: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification [59.96233305733875]
  Classifying traffic is essential for detecting security threats and optimizing network management.<n>We propose a Multi-Instance Encrypted Traffic Transformer (MIETT) to capture both token-level and packet-level relationships.<n>MIETT achieves results across five datasets, demonstrating its effectiveness in classifying encrypted traffic and understanding complex network behaviors.
  arXiv  Detail & Related papers  (2024-12-19T12:52:53Z)
• Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs [19.107744041461316]
  Traffic signal systems (TSCSs) are integral to intelligent traffic management fostering efficient vehicle flow.<n>We propose a novel TSCS framework to realize intelligent traffic edge network.<n>We have crafted a multi-agent soft actor-critic (MA-SAC) reinforcement learning algorithm.
  arXiv  Detail & Related papers  (2024-04-17T02:46:18Z)
• Lens: A Foundation Model for Network Traffic [19.3652490585798]
  Lens is a foundation model for network traffic that leverages the T5 architecture to learn the pre-trained representations from large-scale unlabeled data. We design a novel loss that combines three distinct tasks: Masked Span Prediction (MSP), Packet Order Prediction (POP), and Homologous Traffic Prediction (HTP)
  arXiv  Detail & Related papers  (2024-02-06T02:45:13Z)
• InfraParis: A multi-modal and multi-task autonomous driving dataset [4.6740600790529365]
  We introduce a novel dataset named InfraParis that supports multiple tasks across three modalities: RGB, depth, and infrared. We assess various state-of-the-art baseline techniques, encompassing models for the tasks of semantic segmentation, object detection, and depth estimation.
  arXiv  Detail & Related papers  (2023-09-27T16:07:43Z)
• Graph-based Topology Reasoning for Driving Scenes [102.35885039110057]
  We present TopoNet, the first end-to-end framework capable of abstracting traffic knowledge beyond conventional perception tasks. We evaluate TopoNet on the challenging scene understanding benchmark, OpenLane-V2.
  arXiv  Detail & Related papers  (2023-04-11T15:23:29Z)
• Multi-view Multi-label Anomaly Network Traffic Classification based on MLP-Mixer Neural Network [55.21501819988941]
  Existing network traffic classification based on convolutional neural networks (CNNs) often emphasizes local patterns of traffic data while ignoring global information associations. We propose an end-to-end network traffic classification method.
  arXiv  Detail & Related papers  (2022-10-30T01:52:05Z)
• 5G Traffic Prediction with Time Series Analysis [0.0]
  This project seeks to exploit the traffic history by using it to predict the nature and occurrence of future traffic.<n>By leveraging the power of machine learning we try to achieve three main objectives - classification of the application generating the traffic, prediction of packet arrival intensity and burst occurrence.
  arXiv  Detail & Related papers  (2021-10-07T20:24:34Z)
• MFGNet: Dynamic Modality-Aware Filter Generation for RGB-T Tracking [72.65494220685525]
  We propose a new dynamic modality-aware filter generation module (named MFGNet) to boost the message communication between visible and thermal data. We generate dynamic modality-aware filters with two independent networks. The visible and thermal filters will be used to conduct a dynamic convolutional operation on their corresponding input feature maps respectively. To address issues caused by heavy occlusion, fast motion, and out-of-view, we propose to conduct a joint local and global search by exploiting a new direction-aware target-driven attention mechanism.
  arXiv  Detail & Related papers  (2021-07-22T03:10:51Z)
• LiDAR-based Panoptic Segmentation via Dynamic Shifting Network [56.71765153629892]
  LiDAR-based panoptic segmentation aims to parse both objects and scenes in a unified manner. We propose the Dynamic Shifting Network (DS-Net), which serves as an effective panoptic segmentation framework in the point cloud realm. Our proposed DS-Net achieves superior accuracies over current state-of-the-art methods.
  arXiv  Detail & Related papers  (2020-11-24T08:44:46Z)
• Multi-Agent Routing Value Iteration Network [88.38796921838203]
  We propose a graph neural network based model that is able to perform multi-agent routing based on learned value in a sparsely connected graph. We show that our model trained with only two agents on graphs with a maximum of 25 nodes can easily generalize to situations with more agents and/or nodes.
  arXiv  Detail & Related papers  (2020-07-09T22:16:45Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.