TrapFlow: Controllable Website Fingerprinting Defense via Dynamic Backdoor Learning
- 12 February 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 21 (15566013) , 2610-2625
Abstract
Website fingerprinting (WF) attacks, which covertly monitor user communications to identify the web pages they visit, pose a serious threat to user privacy. Existing WF defenses attempt to reduce attack accuracy by disrupting traffic patterns, but attackers can retrain their models to adapt, making these defenses ineffective. Meanwhile, their high overhead limits deployability. To overcome these limitations, we introduce a novel controllable website fingerprinting defense called TrapFlow based on backdoor learning. TrapFlow exploits the tendency of neural networks to memorize subtle patterns by injecting crafted trigger sequences into targeted website traffic, causing the attacker’s model to build incorrect associations during training. If the attacker attempts to adapt by training on such noisy data, TrapFlow ensures that the model internalizes the trigger as a dominant feature, leading to widespread misclassification across unrelated websites. Conversely, if the attacker ignores these patterns and trains only on clean data, the trigger behaves as an adversarial patch at inference time, causing model misclassification. To achieve this dual effect, we optimize the trigger using the Fast Levenshtein-like distance to maximize both its learnability and distinctiveness from normal traffic. Experiments show that TrapFlow significantly reduces the accuracy of the RF attack from 99% to 6% with 74% data overhead. This compares favorably against two SOTA defenses: FRONT reduces accuracy by only 2% at a similar overhead, while Palette achieves 32% accuracy, but with 48% more overhead. We further validate the practicality of our method in a real Tor network environment.Keywords
All Related Versions
This publication has 44 references indexed in Scilit:
- Exploring the Relationship Between Architectural Design and Adversarially Robust Generalization2023
- A Large-Scale Multiple-objective Method for Black-box Attack Against Object Detection2022
- TrojanFlow: A Neural Backdoor Attack to Deep Learning-based Network Traffic Classifiers2022
- Surakav: Generating Realistic Traces for a Strong Website Fingerprinting Defense2022
- Bias-Based Universal Adversarial Patch Attack for Automatic Check-Out2020
- DFD: Adversarial Learning-based Approach to Defend Against Website Fingerprinting2020
- Neural Cleanse: Identifying and Mitigating Backdoor Attacks in Neural Networks2019
- Identity Mappings in Deep Residual Networks2016
- Peek-a-Boo, I Still See You: Why Efficient Traffic Analysis Countermeasures Fail2012
- A framework for the greedy algorithmDiscrete Applied Mathematics, 2002