InspiringGroup
  • Home
  • Publications
  • People
  • News
  • Awards
  • Join
  • Recent & Upcoming Talks
    • Example Talk
  • Join Us
  • Publications
    • AI and Data Security (with Applied Cryptography)
      • Agent Security
        • Blind Gods and Broken Screens: Architecting a Secure, Intent-Centric Mobile Agent Operating System
        • Anonymization-Enhanced Privacy Protection for Mobile GUI Agents: Available but Invisible
        • BlockA2A: Towards Secure and Verifiable Agent-to-Agent Interoperability
        • Agentic Privacy-Preserving Machine Learning
      • Privacy-Preserving Machine Learning
        • RingSG: Optimal Secure Vertex-Centric Computation for Collaborative Graph Processing
        • CoGNN: Towards Secure and Efficient Collaborative Graph Learning
        • Pencil: Private and Extensible Collaborative Learning without Non-Colluding Assumption
      • AI Security
        • Detection of Adversarial Attacks via Disentangling Natural Images and Perturbations
        • Provenance of Training without Training Data: Towards Privacy-Preserving DNN Model Ownership Verification
        • Good Learning, Bad Performance: A Novel Attack Against RL-Based Congestion Control Systems
        • A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
      • Federated Learning
        • Defending Against Data Reconstruction Attacks in Federated Learning: An Information Theory Approach
    • Networking Infrastructure for AI
      • Intelligent Network Architecture
        • Achieving Interpretable DL-based Web Attack Detection through Malicious Payload Localization
        • Pegasus: A Universal Framework for Scalable Deep Learning Inference on the Dataplane
        • Brain-on-Switch: Towards Advanced Intelligent Network Dataplane via NN-Driven Traffic Analysis at Line-Speed
        • An Efficient Design of Intelligent Network Data Plane
        • FlowTele: Remotely Shaping Traffic on Internet-Scale Networks
      • Datacenter Networking
        • DiffECN: Differential ECN Marking for Datacenter Networks
        • PRED: Performance-oriented Random Early Detection for Consistently Stable Performance in Datacenters
        • Revisiting Random Early Detection Tuning for High-Performance Datacenter Networks
        • Change Management in Physical Network Lifecycle Automation
        • Threshold-Based Routing-Topology Co-Design for Optical Data Center
        • Efficient Forwarding Anomaly Detection in Software-Defined Networks
        • Managing Recurrent Virtual Network Updates in Multi-Tenant Datacenters: A System Perspective
        • Enabling Work-Conserving Bandwidth Guarantees for Multi-Tenant Datacenters via Dynamic Tenant-Queue Binding
    • Secure Networking and Systems Infrastructure
      • AI-Driven Traffic Analysis
        • A Universal Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems
        • Enhancing Website Fingerprinting Attacks against Traffic Drift
        • CertTA: Certified Robustness Made Practical for Learning-Based Traffic Analysis
        • MM4flow: A Pre-trained Multi-modal Model for Versatile Network Traffic Analysis
        • TrafficFormer: An Efficient Pre-trained Model for Traffic Data
        • Training Robust Classifiers for Classfiying Encrypted Traffic under Dynamic Network Conditions
        • Low-Quality Training Data Only? A Robust Framework for Detecting Encrypted Malicious Network Traffic
        • Towards Fine-Grained Webpage Fingerprinting at Scale
        • Learning from Limited Heterogeneous Training Data: Meta-Learning for Unsupervised Zero-day Web Attack Detection across Web Domains
        • Robust Multi-tab Website Fingerprinting Attacks in the Wild
        • Automated Multi-Tab Website Fingerprinting Attack
      • Secure Internet Routing
        • Understanding the Stealthy BGP Hijacking Risk in the ROV Era
        • Learning with Semantics: Towards a Semantics-Aware Routing Anomaly Detection System
        • Secure Inter-domain Routing and Forwarding via Verifiable Forwarding Commitments
        • Enabling Efficient Source and Path Verification via Probabilistic Packet Marking
      • DDoS Attack Prevention
        • Effective DDoS Mitigation via ML-Driven In-Network Traffic Shaping
        • Dynamic Network Security Function Enforcement via Joint Flow and Function Scheduling
        • Umbrella: Enabling ISPs to Offer Readily Deployable and Privacy-Preserving DDoS Prevention Services
        • Practical Proactive DDoS-Attack Mitigation via Endpoint-Driven In-Network Traffic Control
        • MiddlePolice: Toward Enforcing Destination-Defined Policies in the Middle of the Internet
      • Systems Security
        • Cross Container Attacks: The Bewildered eBPF on Clouds
        • Back-Propagating System Dependency Impact for Attack Investigation
        • RapidPatch: Firmware Hotpatching for Real-Time Embedded Devices
        • Unsupervised Contextual Anomaly Detection for Database Systems
        • DeepIntent: Deep Icon-Behavior Learning for Detecting Intention-Behavior Discrepancy in Mobile Apps
        • TorPolice: Towards enforcing service-defined access policies for anonymous communication in the Tor network
    • Web3.0 and Blockchain
      • Web3.0 Infra and Application
        • iSyn: Semi-Automated Smart Contract Synthesis from Legal Financial Agreements
        • Make Web3.0 Connected
      • Zero-Knowledge Proof
        • martFL: Enabling Utility-Driven Data Marketplace with a Robust and Verifiable Federated Learning Architecture
      • HyperService: Interoperability and Programmability Across Heterogeneous Blockchains
  • Courses
    • Hugo Blox
      • Getting Started
      • Guide
        • Project Structure
        • Configuration
        • Formatting
          • Embed Media
          • Buttons
          • Callouts
          • Cards
          • Spoilers
          • Steps
      • Reference
        • Customization
        • Internationalization (i18n)
  • Projects
    • Pandas
    • PyTorch
    • scikit-learn
  • Blog
    • 🎉 Easily create your own simple yet highly customizable blog
    • 🧠 Sharpen your thinking with a second brain
    • 📈 Communicate your results effectively with the best data visualizations
    • 👩🏼‍🏫 Teach academic courses
    • ✅ Manage your projects
  • Experience
  • Awards
  • News
  • Research Topics
    • Secure and Reliable Infrastructure for LLM-powered AI Agents
    • Network Security
    • Privacy-Preserving Machine Learning
    • Blockchain Infrastructures and Web3

A Universal Black-Box Evasion Attack against ML-based Malicious Traffic Detection Systems

Jan 1, 2026·
Zixuan Liu
,
Yi Zhao
Zhuotao Liu
Zhuotao Liu
,
Qi Li
,
Chuanpu Fu
,
Guangmeng Zhou
,
Ke Xu
· 0 min read
Publication
Network and Distributed System Security (NDSS) Symposium 2026
Last updated on Jan 1, 2026
Zhuotao Liu
Authors
Zhuotao Liu
Associate Professor
Enhancing Website Fingerprinting Attacks against Traffic Drift Jan 1, 2026 →

© 2026 Me. This work is licensed under CC BY NC ND 4.0

Made with Hugo Blox — Open Source. Create your site →