Skip to content

wangtz19/Awesome-NTA

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

12 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Awesome Network Traffic Analysis

Awesome Network Traffic Analysis

A curation of awesome papers, datasets and tools about network traffic analysis.

Table of Contents

Papers

Survey

  • A Comprehensive Survey on Network Traffic Synthesis From Statistical Models to Deep Learning, arxiv 2025 [paper]
  • Introducing a Comprehensive, Continuous, and Collaborative Survey of Intrusion Detection Datasets, CSET 2024 [paper]
  • A Survey of Public IoT Datasets for Network Security Research, CST 2023 [paper]
  • SoK: A Critical Evaluation of Efficient Website Fingerprinting Defenses, S&P 2023 [paper]
  • SoK: Pragmatic Assessment of Machine Learning for Network Intrusion Detection, EuroS&P 2023 [paper] [code]
  • Dos and Don'ts of Machine Learning in Computer Security, Security 2022 [paper]

Network Traffic Classification

Offline: Pre-trained Models

  • Convolutions are Competitive with Transformers for Encrypted Traffic Classification with Pre-training, arxiv 2025 [paper]
  • Demystifying Network Foundation Models, NeurIPS 2025 [paper]
  • FlowletFormer: Network Behavioral Semantic Aware Pre-training Model for Traffic Classification, arxiv 2025 [paper]
  • MM4flow: A Pre-trained Multi-modal Model for Versatile Network Traffic Analysis, CCS 2025 [paper]
  • TrafficFormer: An Efficient Pre-trained Model for Traffic Data, S&P 2025 [paper] [code]
  • netFound: Foundation Model for Network Security, arxiv 2025 [paper]
  • A Novel Self-Supervised Framework Based on Masked Autoencoder for Traffic Classification, ToN 2024 [paper]
  • Lens: A Foundation Model for Network Traffic in Cybersecurity, arxiv 2024 [paper]
  • NetBench: A Large-Scale and Comprehensive Network Traffic Benchmark Dataset for Foundation Models, arxiv 2024 [paper]
  • NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mamba, ICNP 2024 [paper] [code]
  • PTU: Pre-trained Model for Network Traffic Understanding, ICNP 2024
  • TrafficGPT: Breaking the Token Barrier for Efficient Long Traffic Analysis and Generation, arxiv 2024 [paper] [code]
  • Flow-MAE: Leveraging Masked AutoEncoder for Accurate, Efficient and Robust Malicious Traffic Classification, RAID 2023 [paper] [code]
  • Listen to Minority: Encrypted Traffic Classification for Class Imbalance with Contrastive Pre-Training, SECON 2023 [paper]
  • NetGPT: Generative Pretrained Transformer for Network Traffic, arxiv 2023 [paper] [code]
  • Yet Another Traffic Classifier: A Masked Autoencoder Based Traffic Transformer with Multi-Level Flow Representation, AAAI 2023 [paper] [code]
  • ET-BERT: A Contextualized Datagram Representation with Pre-training Transformers for Encrypted Traffic Classification, WWW 2022 [paper] [code]
  • Pert: Payload Encoding Representation from Transformer for Encrypted Traffic Classification, ITU 2020 [paper]

Offline: DL/ML

  • Pacc: Protocol-Aware Cross-Layer Compression for Compact Network Traffic Representation, arxiv 2026 [paper]
  • Synecdoche: Efficient and Accurate In-Network Traffic Classification via Direct Packet Sequential Pattern Matching, arxiv 2026 [paper]
  • Cato: End-to-End Optimization of ML-Based Traffic Analysis Pipelines, S&P 2025 [paper]
  • FastFlow: Early Yet Robust Network Flow Classification using the Minimal Number of Time-Series Packets, sigmetrics 2025 [paper] [code]
  • Less is More: Simplifying Network Traffic Classification Leveraging RFCs, arxiv 2025 [paper]
  • Miett: Multi-Instance Encrypted Traffic Transformer for Encrypted Traffic Classification, AAAI 2025 [paper]
  • Multi-view Correlation-aware Network Traffic Detection on Flow Hypergraph, arxiv 2025 [paper]
  • One task to rule them all: A closer look at traffic classification generalizability, arxiv 2025 [paper]
  • Revolutionizing Encrypted Traffic Classification with MH-Net: A Multi-View Heterogeneous Graph Model, AAAI 2025 [paper]
  • SoK: Decoding the Enigma of Encrypted Network Traffic Classifiers, S&P 2025 [paper]
  • The Sweet Danger of Sugar: Debunking Representation Learning for Encrypted Traffic Classification, sigcomm 2025 [paper]
  • TrafficLLM: Enhancing Large Language Models for Network Traffic Analysis with Generic Traffic Representation, arxiv 2025 [paper] [code]
  • When Simple Model Just Works: Is Network Traffic Classification in Crisis?, arxiv 2025 [paper]
  • Fingerprinting the Shadows: Unmasking Malicious Servers with Machine Learning-Powered TLS Analysis, WWW 2024 [paper]
  • Identifying VPN Servers through Graph-Represented Behaviors, WWW 2024 [paper]
  • Mpaf: Encrypted Traffic Classification With Multi-Phase Attribute Fingerprint, TIFS 2024 [paper]
  • ServeFlow: A Fast-Slow Model Architecture for Network Traffic Analysis, arxiv 2024 [paper]
  • Understanding Web Fingerprinting with a Protocol-Centric Approach, RAID 2024 [paper]
  • Classify Traffic Rather Than Flow: Versatile Multi-Flow Encrypted Traffic Classification With Flow Clustering, TNSM 2023 [paper]
  • GGFAST: Automating Generation of Flexible Network Traffic Classifiers, Sigcomm 2023 [paper]
  • ProGraph: Robust Network Traffic Identification With Graph Propagation, ToN 2023 [paper]
  • Replication: Contrastive Learning and Data Augmentation in Traffic Classification Using a Flowpic Input Representation, IMC 2023 [paper]
  • Revolutionizing Cyber Threat Detection with Large Language Models, arxiv 2023 [paper]
  • TFE-GNN: A Temporal Fusion Encoder Using Graph Neural Networks for Fine-grained Encrypted Traffic Classification, WWW 2023 [paper] [code]
  • A few shots traffic classification with mini-FlowPic augmentations, IMC 2022 [paper] [code]
  • MT-FlowFormer: A Semi-Supervised Flow Transformer for Encrypted Traffic Classification, KDD 2022 [paper]
  • MTT: an efficient model for encrypted network traffic classification using multi-task transformer, springer 2022 [paper]
  • Packet Representation Learning for Traffic Classification, KDD 2022 [paper] [code]
  • Seeing Traffic Paths: Encrypted Traffic Classification With Path Signature Features, TIFS 2022 [paper]
  • Accurate Decentralized Application Identification via Encrypted Traffic Analysis Using Graph Neural Networks, TIFS 2021 [paper]
  • New Directions in Automated Traffic Analysis, CCS 2021 [paper]
  • TSCRNN: A novel classification scheme of encrypted traffic based on flow spatiotemporal features for efficient management of IIoT, ComNet 2021 [paper]
  • Deep packet: a novel approach for encrypted traffic classification using deep learning, SoftComputing 2020 [paper]
  • FS-Net: A Flow Sequence Network For Encrypted Traffic Classification, Infocom 2019 [paper] [code]
  • FlowPic: Encrypted Internet Traffic Classification is as Easy as Image Recognition, Infocom workshop 2019 [paper] [code]
  • Seq2Img: A sequence-to-image based approach towards IP traffic classification using convolutional neural networks, BigData 2017 [paper]
  • A preliminary performance comparison of five machine learning algorithms for practical IP traffic flow classification, sigmetrics 2006 [paper]
  • BLINC: Multilevel Traffic Classification in the Dark, sigcomm 2005 [paper]
  • Internet traffic classification using bayesian analysis techniques, sigmetrics 2005 [paper]

Online: DL/ML (In-Network)

  • Brain-on-Switch: Towards Advanced Intelligent Network Data Plane via NN-Driven Traffic Analysis at Line-Speed, NSDI 2024 [paper] [code]
  • Caravan: Practical Online Learning of In-Network ML Models with Labeling Agents, OSDI 2024 [paper]
  • High-Throughput Stateless-But-Complex Packet Processing Within a Tbps Programmable Switch, ICNP 2024 [paper]
  • IIsy: Hybrid In-Network Classification Using Programmable Switches, ToN 2024 [paper] [code]
  • Linc: Enabling Low-Resource in-Network Classification and Incremental Model Update, ICNP 2024 [paper] [code]
  • Leo: Online ML-based Traffic Classification at Multi-Terabit Line Rate, NSDI 2024 [paper] [code]
  • Recursive Multi-Tree Construction With Efficient Rule Sifting for Packet Classification on FPGA, ToN 2024 [paper] [code]

Network Traffic Generation

  • DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model, NeurIPS 2024 [paper]
  • Diffusion Model-based Mobile Traffic Generation with Open Data for Network Planning and Optimization, KDD 2024 [paper]
  • Feasibility of State Space Models for Network Traffic Generation, NAIC 2024 [paper]
  • NetDiff: A Service-Guided Hierarchical Diffusion Model for Network Flow Trace Generation, CoNext3 2024 [paper]
  • Synthetic and privacy-preserving traffic trace generation using generative ai models for training network intrusion detection systems, elsevier 2024 [paper] [code]
  • Datacenter Network Deserves Better Traffic Models, Hotnets 2023 [paper]
  • NetDiffus: Network Traffic Generation by Diffusion Models through Time-Series Imaging, arxiv 2023 [paper] [code]
  • NetDiffusion: Network Data Augmentation Through Protocol-Constrained Traffic Generation, SIGMETRICS 2023 [paper] [code]
  • PAC-GPT: A novel approach to generating synthetic network traffic with GPT-3, arxiv 2023 [paper] [code]
  • Locality Matters! Traffic Demand Modeling in Datacenter Networks, APNET 2022 [paper]
  • Necstgen: An approach for realistic network traffic generation using deep learning, GLOBECOM 2022 [paper] [code]
  • Practical GAN-based synthetic IP header trace generation using NetShare, SIGCOMM 2022 [paper] [code]
  • Stan: Synthetic Network Trafic Generation with Generative Neural Models, arxiv 2021 [paper] [code]
  • Using GANs for Sharing Networked Time Series Data: Challenges, Initial Promise, and Open Questions, IMC 2020 [paper] [code]

Network Intrusion Detection

Offline: DL/ML

  • MalMoE: Mixture-of-Experts Enhanced Encrypted Malicious Traffic Detection Under Graph Drift, arxiv 2026
  • Continual Learning with Strategic Selection and Forgetting for Network Intrusion Detection, arxiv 2025 [paper]
  • Generative Active Adaptation for Drifting and Imbalanced Network Intrusion Detection, arxiv 2025
  • Hierarchical Local-Global Feature Learning for Few-shot Malicious Traffic Detection, arxiv 2025
  • Self-Supervised Learning of Graph Representations for Network Intrusion Detection, arxiv 2025
  • $\mathsf{TCG}\text{-}\mathsf{IDS}$ : Robust Network Intrusion Detection via Temporal Contrastive Graph Learning, TIFS 2025 [paper]
  • ContraMTD: An Unsupervised Malicious Network Traffic Detection Method based on Contrastive Learning, WWW 2024 [paper]
  • Delm: Deep Ensemble Learning Model for Anomaly Detection in Malicious Network Traffic-based Adaptive Feature Aggregation and Network Optimization, TOPS 2024 [paper]
  • Detecting Tunneled Flooding Traffic via Deep Semantic Analysis of Packet Length Patterns, CCS 2024 [paper]
  • Device Identification and Anomaly Detection in IoT Environments, IOT 2024 [paper]
  • Divide, Conquer, and Coalesce: Meta Parallel Graph Neural Network for IoT Intrusion Detection at Scale, WWW 2024 [paper]
  • Enhanced Few-Shot Malware Traffic Classification via Integrating Knowledge Transfer With Neural Architecture Search, TIFS 2024 [paper]
  • Foss: Towards Fine-Grained Unknown Class Detection Against the Open-Set Attack Spectrum With Variable Legitimate Traffic, ToN 2024 [paper]
  • K-GetNID: Knowledge-Guided Graphs for Early and Transferable Network Intrusion Detection, TIFS 2024 [paper]
  • Mateen: Adaptive Ensemble Learning for Network Anomaly Detection, RAID 2024 [paper] [code]
  • NetVigil: Robust and Low-Cost Anomaly Detection for East-West Data Center Security, NSDI 2024 [paper] [code]
  • Practical Cyber Attack Detection With Continuous Temporal Graph in Dynamic Network System, TIFS 2024 [paper]
  • RFG-HELAD: A Robust Fine-Grained Network Traffic Anomaly Detection Model Based on Heterogeneous Ensemble Learning, TIFS 2024 [paper]
  • Relative Frequency-Rank Encoding for Unsupervised Network Anomaly Detection, ToN 2024 [paper]
  • Spider: A Semi-Supervised Continual Learning-based Network Intrusion Detection System, Infocom 2024 [paper]
  • TMG-GAN: Generative Adversarial Networks-Based Imbalanced Learning for Network Intrusion Detection, TIFS 2024 [paper]
  • TrafCL: Robust Encrypted Malicious Traffic Detection via Contrastive Learning, CIKM 2024 [paper]
  • Trident: A Universal Framework for Fine-Grained and Class-Incremental Unknown Traffic Detection, WWW 2024 [paper] [code]
  • 3D-IDS: Doubly Disentangled Dynamic Intrusion Detection, KDD 2023 [paper]
  • Application of a Dynamic Line Graph Neural Network for Intrusion Detection With Semisupervised Learning, TIFS 2023 [paper]
  • CPS-GUARD: Intrusion detection for cyber-physical systems and IoT devices using outlier-aware deep autoencoders, CS 2023 [paper]
  • ERNN: Error-Resilient RNN for Encrypted Traffic Detection towards Network-Induced Phenomena, TDSC 2023 [paper]
  • Learning from Limited Heterogeneous Training Data: Meta-Learning for Unsupervised Zero-Day Web Attack Detection across Web Domains, CCS 2023 [paper]
  • Point Cloud Analysis for ML-Based Malicious Traffic Detection: Reducing Majorities of False Positive Alarms, CCS 2023 [paper]
  • TS-IDS: Traffic-aware self-supervised learning for IoT Network Intrusion Detection, KBS 2023 [paper]
  • Toward Early and Accurate Network Intrusion Detection Using Graph Embedding, TIFS 2023 [paper]
  • Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection, NeurIPS 2023 [paper]
  • Anomal-E: A self-supervised network intrusion detection system based on graph neural networks, arxiv 2022 [paper]
  • Encrypted Malware Traffic Detection via Graph-based Network Analysis, RAID 2022 [paper]
  • Conditional Variational Auto-Encoder and Extreme Value Theory Aided Two-Stage Learning Approach for Intelligent Fine-Grained Known/Unknown Intrusion Detection, TIFS 2021 [paper]
  • E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT, arxiv 2021 [paper] [code]
  • Enad: An Ensemble Framework for Unsupervised Network Anomaly Detection, CSR 2021 [paper]
  • Graph-based Solutions with Residuals for Intrusion Detection: the Modified E-GraphSAGE and E-ResGAT Algorithms, arxiv 2021 [paper]
  • Random Partitioning Forest for Point-Wise and Collective Anomaly Detection - Application to Network Intrusion Detection, TIFS 2021 [paper]
  • Unveiling the potential of Graph Neural Networks for robust Intrusion Detection, arxiv 2021 [paper]
  • Automating Botnet Detection with Graph Neural Networks, arxiv 2020 [paper]
  • Anomaly-Based Intrusion Detection From Network Flow Features Using Variational Autoencoder, IEEE Access 2020 [paper]
  • Improving Attack Detection Performance in NIDS Using GAN, COMPSAC 2020 [paper]
  • Passban IDS: An Intelligent Anomaly-Based Intrusion Detection System for IoT Edge Devices, ITJ 2020 [paper]
  • Throwing Darts in the Dark? Detecting Bots with Limited Data using Neural Data Augmentation, S&P 2020 [paper]
  • Unsupervised learning approach for network intrusion detection system using autoencoders, JS 2019 [paper]
  • Detecting HTTP-based application layer DoS attacks on web servers in the presence of sampling, Computer Networks 2017 [paper]

Online: DL/ML (In-Network)

  • AOC-IDS: Autonomous Online Framework with Contrastive Learning for Intrusion Detection, Infocom 2024 [paper] [code]
  • Effective DDoS Mitigation via ML-Driven In-Network Traffic Shaping, TDSC 2024 [paper]
  • Enhancing Network Attack Detection with Distributed and In-Network Data Collection System, Security 2024 [paper]
  • Online Self-Supervised Deep Learning for Intrusion Detection Systems, TIFS 2024 [paper]
  • Proteus: A Difficulty-Aware Deep Learning Framework for Real-Time Malicious Traffic Detection, ICNP 2024 [paper]
  • Rids: Towards Advanced IDS via RNN Model and Programmable Switches Co-Designed Approaches, Infocom 2024 [paper] [code]
  • Detecting Unknown Encrypted Malicious Traffic in Real Time via Flow Interaction Graph Analysis, NDSS 2023 [paper] [code]
  • HorusEye: A Realtime IoT Malicious Traffic Detection Framework using Programmable Switches, Security 2023 [paper] [code]
  • Real-Time Malicious Traffic Detection With Online Isolation Forest Over SD-WAN, TIFS 2023 [paper]
  • Realtime Robust Malicious Traffic Detection via Frequency Domain Analysis, CCS 2021 [paper]
  • Kitsune: An Ensemble of Autoencoders for Online Network Intrusion Detection, NDSS 2018 [paper] [code]

Robustness

  • AN-Net: an Anti-Noise Network for Anonymous Traffic Classification, WWW 2024 [paper]
  • Cactus: Obfuscating Bidirectional Encrypted TCP Traffic at Client Side, TIFS 2024 [paper]
  • Detecting and Mitigating Sampling Bias in Cybersecurity with Unlabeled Data, Security 2024 [paper]
  • Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic, NDSS 2024 [paper] [code]
  • MCRe: A Unified Framework for Handling Malicious Traffic With Noise Labels Based on Multidimensional Constraint Representation, TIFS 2024 [paper]
  • ProGen: Projection-Based Adversarial Attack Generation Against Network Intrusion Detection, TIFS 2024 [paper]
  • ReCDA: Concept Drift Adaptation with Representation Enhancement for Network Intrusion Detection, KDD 2024 [paper]
  • Scrr: Stable Malware Detection under Unknown Deployment Environment Shift by Decoupled Spurious Correlations Filtering, TDSC 2024 [paper]
  • Anomaly Detection in the Open World: Normality Shift Detection, Explanation, and Adaptation, NDSS 2023 [paper] [code]
  • Bars: Local Robustness Certification for Deep Learning based Traffic Analysis Systems, NDSS 2023 [paper] [code]
  • CADE: Detecting and Explaining Concept Drift Samples for Security Applications, Security 2021 [paper] [code]
  • Fare: Enabling Fine-grained Attack Categorization under Low-quality Labeled Data, NDSS 2021 [paper]

Explainability

  • Building Transparency in Deep Learning-Powered Network Traffic Classification: A Traffic-Explainer Framework, arxiv 2025 [paper]
  • Genos: General In-Network Unsupervised Intrusion Detection by Rule Extraction, Infocom 2024 [paper]
  • IDS-Agent: An LLM Agent for Explainable Intrusion Detection in IoT Networks, NeurIPS Workshop 2024
  • Rules Refine the Riddle: Global Explanation for Deep Learning-Based Anomaly Detection in Security Applications, CCS 2024 [paper]
  • Towards Explainable Network Intrusion Detection using Large Language Models, arxiv 2024 [paper]
  • True Attacks, Attack Attempts, or Benign Triggers? An Empirical Measurement of Network Alerts in a Security Operations Center, Security 2024 [paper]
  • Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly Detection, NeurIPS 2024 [paper]
  • Everybody’s Got ML, Tell Me What Else You Have: Practitioners’ Perception of ML-Based Security Tools and Explanations, S&P 2023 [paper]
  • Finer: Enhancing State-of-the-art Classifiers with Feature Attribution to Facilitate Security Analysis, CCS 2023 [paper]
  • Towards Understanding Alerts raised by Unsupervised Network Intrusion Detection Systems, RAID 2023 [paper]
  • Interpreting Unsupervised Anomaly Detection in Security via Rule Extraction, NeurIPS 2023 [paper]
  • xNIDS: Explaining Deep Learning-based Network Intrusion Detection Systems for Active Intrusion Responses, Security 2023 [paper] [code]
  • AI/ML for Network Security: The Emperor has no Clothes, CCS 2022 [paper] [code]
  • I $^{2}$ RNN: An Incremental and Interpretable Recurrent Neural Network for Encrypted Traffic Classification, TDSC 2022 [paper]

Website Fingerprinting

  • Contrastive Fingerprinting: A Novel Website Fingerprinting Attack over Few-shot Traces, WWW 2024 [paper]
  • Fingerprinting Obfuscated Proxy Traffic with Encapsulated TLS Handshakes, Security 2024 [paper]
  • Robust Multi-tab Website Fingerprinting Attacks in the Wild, S&P 2023 [paper]
  • Transformer-based Model for Multi-tab Website Fingerprinting Attack, CCS 2023 [paper]

Mobile App Fingerprinting

  • AppSniffer: Towards Robust Mobile App Fingerprinting Against VPN, WWW 2023 [paper] [code]
  • FOAP: Fine-Grained Open-World Android App Fingerprinting, Security 2022 [paper]
  • FlowPrint: Semi-Supervised Mobile-App Fingerprinting on Encrypted Network Traffic, NDSS 2020 [paper] [code]
  • Robust Smartphone App Identification via Encrypted Network Traffic Analysis, TIFS 2018 [paper] [code]

APT Detection & Provenance Graph IDS

  • ORTHRUS: Achieving High Quality of Attribution in Provenance-based Intrusion Detection Systems, Security 2025 [paper] [code]
  • Flash: A Comprehensive Approach to Intrusion Detection via Provenance Graph Representation Learning, S&P 2024 [paper] [code]
  • Kairos: Practical Intrusion Detection and Investigation using Whole-system Provenance, S&P 2024 [paper] [code]
  • MAGIC: Detecting Advanced Persistent Threats via Masked Graph Representation Learning, Security 2024 [paper] [code]
  • Nodlink: An Online System for Fine-Grained APT Attack Detection and Investigation, NDSS 2024 [paper] [code]
  • Understanding and Bridging the Gap Between Unsupervised Network Representation Learning and Security Analytics, S&P 2024 [paper]
  • Distdet: A Cost-Effective Distributed Cyber Threat Detection System, Security 2023 [paper]
  • EdgeTorrent: Real-time Temporal Graph Representations for Intrusion Detection, RAID 2023 [paper]
  • Prographer: An Anomaly Detection System based on Provenance Graph Embedding, Security 2023 [paper]
  • Euler: Detecting Network Lateral Movement via Scalable Temporal Link Prediction, NDSS 2022 [paper] [code]
  • SHADEWATCHER: Recommendation-guided Cyber Threat Analysis using System Audit Records, S&P 2022 [paper] [code]
  • THREATRACE: Detecting and Tracing Host-Based Threats in Node Level Through Provenance Graph Learning, TIFS 2022 [paper] [code]
  • ATLAS: A Sequence-based Learning Approach for Attack Investigation, Security 2021 [paper] [code]
  • DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications, CCS 2021 [paper] [code]
  • Hopper: Modeling and Detecting Lateral Movement, Security 2021 [paper]
  • Detecting Lateral Movement in Enterprise Computer Networks with Unsupervised Graph AI, RAID 2020 [paper]
  • Unicorn: Runtime Provenance-Based Detector for Advanced Persistent Threats, NDSS 2020 [paper] [code]

Traffic Analysis under Distribution Shift

  • CD-Net: Robust mobile traffic classification against apps updating, ComSec 2025 [paper]
  • Detection of Unknown Attacks Through Encrypted Traffic: A Gaussian Prototype-Aided Variational Autoencoder Framework, TIFS 2025 [paper]
  • FG-SAT: Efficient Flow Graph for Encrypted Traffic Classification Under Environment Shifts, TIFS 2025 [paper]
  • Facing Anomalies Head-On: Network Traffic Anomaly Detection via Uncertainty-Inspired Inter-Sample Differences, WWW 2025 [paper]
  • M3S-UPD: Efficient Multi-Stage Self-Supervised Learning for Fine-Grained Encrypted Traffic Classification with Unknown Pattern Discovery, arxiv 2025 [paper]
  • Reliable Open-Set Network Traffic Classification, TIFS 2025 [paper]
  • Respond to Change With Constancy: Instruction-Tuning With LLM for Non-I.I.D. Network Traffic Classification, TIFS 2025 [paper]
  • Training Robust Classifiers for Classifying Encrypted Traffic under Dynamic Network Conditions, CCS 2025 [paper]
  • ECNet: Robust Malicious Network Traffic Detection With Multi-View Feature and Confidence Mechanism, TIFS 2024 [paper]
  • TrafficLLM: LLMs for improved open-set encrypted traffic analysis, arxiv 2024 [paper] [code]
  • Extensible Machine Learning for Encrypted Network Traffic Application Labeling via Uncertainty Quantification, TAI 2023 [paper]
  • Realistic Website Fingerprinting By Augmenting Network Traces, CCS 2023 [paper]
  • Rosetta: Enabling Robust TLS Encrypted Traffic Classification in Diverse Network Environments with TCP-Aware Traffic Augmentation, Security 2023 [paper]
  • Zero-relabelling mobile-app identification over drifted encrypted network traffic, ComNet 2023 [paper]
  • Distributionally Robust Neural Networks for Group Shifts: On the Importance of Regularization for Worst-Case Generalization, ICLR 2020 [paper]
  • Transfer Learning with Dynamic Adversarial Adaptation Network, ICDM 2019 [paper]
  • Optimized Invariant Representation of Network Traffic for Detecting Unseen Malware Variants, Security 2016 [paper]

Datasets & Benchmarks

  • Exploring QUIC Dynamics: A Large-Scale Dataset for Encrypted Traffic Analysis, arxiv 2025 [paper]
  • A Large-Scale Mobile Traffic Dataset For Mobile Application Identification, computer journal 2024 [paper]
  • Bad Design Smells in Benchmark NIDS Datasets, EuroS&P 2024 [paper]
  • Evaluating Standard Feature Sets Towards Increased Generalisability and Explainability of ML-Based Network Intrusion Detection, ToN-IoT:BoT-IoT 2022 [paper]
  • ToN_IoT: The Role of Heterogeneity and the Need for Standardization of Features and Attack Types in IoT Network Intrusion Data Sets, IOT 2022 [paper]
  • A Detailed Analysis of the CICIDS2017 Benchmark Dataset for Intrusion Detection, 2021
  • Detection of DoH Tunnels using Time-series Classification of Encrypted Traffic, DoH 2020 [paper]
  • Developing Realistic Distributed Denial of Service (DDoS) Attack Dataset and Taxonomy, CICDDoS2019 2019 [paper]
  • Toward Generating a New Intrusion Detection Dataset and Intrusion Traffic Characterization, CICIDS 2018 [paper]
  • Characterization of Tor Traffic using Time based Features, ISCXTor2016 2017 [paper]
  • Characterization of Encrypted and VPN Traffic using Time-related Features, ISCXVPN2016 2016 [paper]

Datasets

Encrypted Traffic & Anonymity

Dataset Year Description Classes Format Size Link
Darknet 2020 (CICDarknet2020) 2020 Detection and characterisation of darknet (Tor + VPN) traffic, supporting early malware monitoring and post-outbreak analysis. 8 CSV link
Tor-nonTor dataset (ISCXTor2016) 2016 Tor vs non-Tor traffic classification using time-based flow features extracted with ISCXFlowMeter. 7 (browsing, email, chat, audio, video, FTP, VoIP) pcap CSV 22 GB link
VPN-nonVPN traffic dataset (ISCXVPN2016) 2016 VPN vs non-VPN traffic classification using time-related flow features. 14 (VoIP, VPN-VoIP, P2P, VPN-P2P, …) pcap CSV 28 GB link
AppSniffer mobile-app dataset (×4) Four labelled mobile-app traffic captures released with AppSniffer (WWW '23). link

Intrusion Detection & Attacks

DDoS

Dataset Year Description Classes Format Size Link
Realistic IDS — DoS and spoofing attack in IoV (CICIoV2024) 2024 Realistic IDS evaluation for in-vehicle (IoV) CAN-bus DoS and spoofing attacks captured on a 2019 Ford vehicle. 2 (DoS, spoofing) CSV 6.3 MB link
CICEV2023 / CICDataset_Organized (CICEV2023 & CICDataset_Organized) 2023 Detection of DDoS attacks against electric-vehicle (EV) charging infrastructure under four simulated attack scenarios. 4 attack scenarios json link
DDoS evaluation dataset (CIC-DDoS2019) 2019 Benchmark for distributed denial-of-service attack detection algorithms. 13 pcap CSV multi link
CIC UNSW-NB15 Augmented Dataset (CIC-UNSW-NB15) Augmented UNSW-NB15 derivative with new CICFlowMeter features for adversarial NIDS evaluation. 10 (9 attack types + benign) CSV 1.8 GB link

DNS / DoH Tunneling

Dataset Year Description Classes Format Size Link
CIC Bell DNS EXF 2021 (CICBellEXFDNS2021) 2021 Low-rate covert data exfiltration over DNS tunnels. 3 (heavy attack, light attack, benign) pcap CSV 270.8 MB link
DNS over HTTPS (CIRA-CIC-DoHBrw2020) 2020 Encrypted DNS-over-HTTPS traffic for covert-channel and tunnel detection. 3 (benign DoH, malicious DoH, non-DoH) pcap CSV link
CIC Bell DNS 2021 (CICBellDNS2021) Malicious-domain detection using lexical, DNS-statistical, and third-party features. 4 (benign, spam, phishing, malware) CSV 400K benign / 13,011 malicious samples link

Botnet

Dataset Year Description Classes Format Size Link
ISCX botnet dataset 2014 (ISCX-Bot-2014) 2014 Composite botnet detection benchmark mixing benign traffic with multiple botnet families. 7 (train) / 16 (test) archive 5.3 GB train / 8.5 GB test link

IDS / IoT

Dataset Year Description Classes Format Size Link
Attack vectors in healthcare (CICIoMT 2024) 2024 Security evaluation for Internet-of-Medical-Things devices over Wi-Fi/MQTT and Bluetooth Low Energy. 5 (DDoS, DoS, Recon, MQTT, spoofing) pcap CSV 10 GB link
CIC EV charger attack dataset 2024 (CICEVSE2024) 2024 EV-charging-station security: behavioural analysis and binary/multi-class anomaly detection from ~900 hardware performance counters. multi CSV 2.6 GB link
A real-time IoT attack benchmark (CICIoT 2023) 2023 Large-scale IoT attack benchmark with 33 attacks across 105 IoT devices. 7 (DDoS, DoS, Recon, Web, Brute Force, Spoofing, Mirai) pcap CSV multi link
iCloud Private Relay traffic-analysis dataset 2023 · UMass Website-fingerprinting and traffic-correlation experiments against Apple iCloud Private Relay (UMass, ASIACCS '23). n/a pcap CSV 1.8 GB link
IoT profiling dataset (CICIoT 2022) 2022 IoT device profiling, behavioural analysis and identification across Power/Idle/Interactive/Scenario/Active/Attack regimes. 3 device classes (Audio, Camera, Home Automation) pcap CSV <5 GB link
IPS/IDS dataset on AWS (CSE-CIC-IDS2018) 2018 Network-based anomaly IDS evaluation on AWS-hosted infrastructure. 7 attack classes (Brute Force, Heartbleed, Botnet, DoS, DDoS, Web, Infiltration) CSV link
Intrusion detection evaluation dataset (CIC-IDS2017) 2017 IDS/IPS evaluation benchmark with diverse attack scenarios. 8 (FTP/SSH brute force, DoS, Heartbleed, Web, Infiltration, Botnet, DDoS) pcap CSV ~51.1 GB link
CSIC 2010 2010 HTTP web-attack detection benchmark. link
Enriching IoT datasets (Enriched_IOT_Datasets) Horizontally and vertically enriched combinations of Bot-IoT and TON-IoT for security analytics. multi CSV link

Application & Mobile-App Identification

Dataset Year Description Classes Format Size Link
CSTNET 2023 2023 · CAS / CSTNET Anonymised institutional Internet traffic from CSTNET (CAS). json link
CW-100 2018 2023 Encrypted mobile-app classification benchmark (100 apps). json link
NUDT MobileTraffic Dataset 2023 · Network Forensics Research Lab Anonymised mobile-app traffic with three label levels: 22 categories, 350 apps, 9 brands × 94 phone models. 22 traffic categories / 350 apps / 9 brands / 94 models pcap CSV 293 GB link
Application Based Network Traffic Dataset 2021 Packet captures of 22 commonly used desktop applications (Kaggle). 22 applications PCAP 6.96 GB link
CrossNet2021 2021 Cross-network mobile-app classification benchmark used by ProGraph. link
MaMPF 2018 · Chang Liu; Zigang Cao; Gang Xiong; Gaopeng Gou; Siu-Ming Yiu; Longtao He Encrypted-traffic classification using multi-attribute Markov probability fingerprints over length-block sequences. 950,000+ encrypted flows link
Cross-Platform iOS/Android Apps (Northeastern Recon) 2017 · The Northeastern University Cross-country (China / India / US) mobile-app traffic captured on Nexus 5 (Android 6) and iPhone 5 / 5s (iOS 10). pcap link
International Privacy Risks of Mobile Apps 2017 · Jingjing Ren, Daniel J. Dubois, David Choffnes Manual five-minute interaction traces for the top 100 iOS and Android apps to study cross-app privacy leakage. pcap 8 GB link
ANDRUBIS 2016 · Martina Lindorfer, Matthias Neugschwandtner, Lukas Weichselbaum, Yanick Fratantonio, Victor van der Veen, Christian Platzer Static + dynamic analysis traces for over 1M Android apps (~40 % malicious). CSV pcap 1,000,000+ Android apps link
USTC TFC 2016 2016 · USTC Encrypted-traffic classification benchmark from USTC. pcap link
UNIBS-2009 2009 · U. Brescia Edge-router traffic from a U. Brescia campus network covering 20 workstations. multi by request 27 GB raw / 2.7 GB anonymised + payload-stripped link
Moore & Zuev hand-labelled flows 2005 · Andrew W. Moore, Denis Zuev (Queen Mary, University of London) Hand-labelled flow dataset (10 application classes) accompanying Moore & Zuev's SIGMETRICS '05 paper, in WEKA format. paid 5–17 MB (gzip) link
MAWI Working Group Traffic Archive 1999-2024 · WIDE Project Long-running (1999–) backbone Internet trace archive captured via tcpdump on the WIDE backbone, with anonymised IPs. pcap link
MAWILab daily-updated · WIDE Project Daily-updated network anomaly labels derived from MAWI traces by combining multiple independent detectors with a graph-based scheme. web view + CSV link

Concept Drift

Dataset Year Description Classes Format Size Link
APP-53 2023 2023 Mobile-app traffic with 53 classes for concept-drift evaluation. link

Malware Traffic

Dataset Year Description Classes Format Size Link
Evasive PDF Mal 2022 (Evasive-PDFMal2022) 2022 Evasive malicious-PDF detection benchmark; evasive samples are filtered via K-means over 32 features. multi archive 1.2 GB link
Malware Memory Analysis (CIC MalMem 2022) 2022 Memory-dump benchmark for detecting obfuscated malware. multi CSV 358 MB link
Android Malware (CIC MalDroid 2020) 2020 Five-class Android malware benchmark (Adware, Banking, SMS, Riskware, Benign) with semi-supervised baselines. 5 (Adware, Banking, SMS, Riskware, Benign) APK files Capturing-logs CSV files: 111 GB+ link
CCCS-CIC-AndMal2020 (Android Malware 2020) 2020 Android malware benchmark co-developed with the Canadian Centre for Cyber Security; 200 K malicious + 200 K benign apps. 14 categories / 191 malware families CSV 400 K apps link
Android Adware and General Malware Dataset (CIC-AAGM2017) 2017 Android adware and general-malware network traffic captured on real devices. 3 (Adware, General Malware, Benign) pcap CSV 9.1 GB link
Android Malware Dataset (CIC-AndMal2017) 2017 Android malware traffic captured on real smartphones to evade emulator detection. 4 (Adware, Ransomware, Scareware, SMS) pcap link

Tools

Packet Parsing

Tool Type Language Description Link
Wireshark GUI C / C++ De-facto graphical network-protocol analyser; deep dissection of 3000+ protocols, capture filters (BPF) and display filters, follow-stream view, decryption (TLS, WPA, …), and a rich plug-in ecosystem. link
tshark CLI C / C++ Command-line companion to Wireshark sharing the same dissector library; ideal for batch processing and scripted feature extraction (e.g. tshark -r in.pcap -T fields -e ip.src -e tls.handshake.extensions_server_name). link
tcpdump CLI C Veteran libpcap-based capture and inspection tool; lightweight, ubiquitous on UNIX, the canonical source for raw pcap captures. link
Zeek CLI / framework C++ Stateful protocol analyser (formerly Bro) that turns live or replayed traffic into structured logs (conn / dns / ssl / http / files). Many academic NIDS datasets ship Zeek-derived features. link
Scapy Python library Python Programmable packet-manipulation framework — sniff, craft, send, fuzz and dissect arbitrary protocols; widely used for traffic generation in research code. link
PyShark Python library Python Pythonic wrapper around tshark; exposes the full Wireshark dissector tree as Python objects for scripted field-level analysis. link
dpkt Python library Python Pure-Python, zero-dependency pcap parser focused on L2–L4 plus common L7 protocols; often 10–50× faster than PyShark for ML feature extraction loops. link
nFStream Python library Python / C High-throughput pcap-to-flow streaming with 80+ statistical features and optional nDPI application identification; modern alternative to CICFlowMeter for ML pipelines. link
flowcontainer Python library Python Lightweight tshark wrapper that turns a pcap into per-flow records (5-tuple, packet sizes, inter-arrival times, payload bytes, TLS SNI, HTTP host, …) ready for ML feature engineering. link

Packet Splitting / Editing

Tool Type Language Description Link
SplitCap CLI (Windows / .NET) C# Splits a pcap into smaller pcaps per flow, host pair, MAC, port, packet count or seconds; widely cited preprocessing baseline. link
splitpcap CLI / Python library Python Open-source SplitCap-style tool with extra modes (per-session, per-direction, sampling); cross-platform and embeddable in Python pipelines. link
netkit CLI Rust High-throughput pcap manipulation toolkit (split / merge / extract / stats) written in Rust; targets million-flow corpora where Python tooling becomes a bottleneck. link
ShieldGPT pcap_tool CLI C++ Pcap preprocessing utilities released alongside ShieldGPT — flow splitting, sampling, filtering, anonymisation and dataset packaging for LLM-based traffic analysis. link
editcap CLI (ships with Wireshark) C Pcap surgery swiss-army knife: split by chunk count or seconds, trim time ranges, fix timestamps, change link-layer encapsulation, anonymise MACs, deduplicate, and convert between pcap/pcapng. link
mergecap CLI (ships with Wireshark) C Counterpart to editcap: merge multiple pcaps preserving timestamps; concatenate or interleave by capture time. link
pcapfix CLI C Repairs truncated or corrupted pcap and pcapng files; useful when reusing legacy academic captures with broken global / packet headers. link

Flow Feature Extraction

Tool Type Language Description Link
CICFlowMeter CLI / library Java Reference flow-feature extractor used to label every CIC-* dataset (CIC-IDS2017, CIC-DDoS2019, …); the 80-feature schema mirrored by most published NIDS baselines. link
Argus CLI / daemon C Long-running bidirectional flow-record generator producing detailed per-flow records (counts, bytes, timing, performance metrics); standard for academic flow analytics for two decades. link
Tranalyzer2 CLI C Modular plug-in-based flow analyzer that emits 700+ features per flow; supports live capture, offline pcap, and IPv6. link
joy CLI C Cisco-released flow extractor designed for encrypted-traffic analysis: TLS metadata, byte distribution, packet length / inter-arrival sequences, DNS / HTTP enrichment. link

Traffic Replay / Generation

Tool Type Language Description Link
tcpreplay CLI suite C Replay pcaps onto live interfaces at controlled rates with tcpreplay, rewrite addresses with tcprewrite, and run interactive client/server replay with tcpliveplay. The default tool for testbed-based NIDS evaluation. link
MoonGen CLI Lua / DPDK Scriptable line-rate (10–100 Gbps) packet generator built on DPDK; the standard reproducible testbed used in NSDI / SIGCOMM dataplane evaluations. link
TRex CLI / Python API C++ / Python (DPDK) Cisco's stateful traffic generator: supports realistic application emulation, multi-million flow scaling, and a Python client for orchestrated experiments. link

Anonymization

Tool Type Language Description Link
CryptoPAn C library / CLI C Prefix-preserving IP-address anonymisation; the de-facto scheme cited in MAWI, CAIDA and most anonymised-trace dataset releases. link
tcpdpriv CLI C Older but still-used trace anonymiser with flexible per-field policies (drop / random / prefix-preserving). The original tool used by the WIDE / MAWI archives. link
PktAnon CLI C++ Protocol-aware pcap anonymiser from KIT with an XML/YAML profile describing which headers, payloads, MACs and IPs to strip or pseudonymise. link

License

CC0

To the extent possible under law, the maintainers have waived all copyright and related rights to this work under CC0 1.0 Universal. The list itself is a curation of publicly available paper metadata; copyright on the underlying papers and code repositories belongs to their respective authors.

About

A curation of awesome papers, datasets and tools about network traffic analysis.

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors