Local Order Matters: A Lightweight CPU-Trainable CNN for Website Fingerprinting on Defended Tor Traffic
Organizations: Department of Electrical and Computer Engineering, Duke University, Durham, NC 27708, United States · Department of Computer Science, Rice University, Houston, TX 77005, United States
Abstract
Website fingerprinting (WF) attacks let a passive adversary infer which site a Tor user visits from the encrypted cell sequence. On undefended traffic, hand-crafted-feature attacks are already near-ceiling, so deep learning offers only a marginal advantage there. We show that the decisive regime is defended traffic: against the FRONT padding defense, which injects dummy cells that corrupt the volume and count features feature attacks rely on, a compact 95,103-parameter 1-D convolutional network trained on the raw cell-direction sequence, on CPU only, stays robust while three implemented direction-only feature baselines degrade. On the closed-world WFlib FRONT set (95 sites), our model reaches 54.2% top-1 accuracy versus 38.5% for the strongest implemented feature baseline (k-FP-style RF), a gain of 15.7 percentage points (3 seeds; seed-0 paired-bootstrap 95% CI [+14.5, +17.0] pp on per-trace correctness, excluding zero). On undefended traffic the CNN reaches 94.1% versus 92.3% for k-FP-style RF. A controlled order-ablation permutes only nonzero traffic cells within each trace, preserving direction counts, retained length, and trailing zero-padding positions while destroying traffic order. This collapses the CNN below every feature baseline (from 54.2% to 7.6%, a 46.6 pp drop), showing that the model depends strongly on order-derived information under FRONT.
Figures & tables
| Method | Accuracy | Macro-F1 |
|---|---|---|
| Wang-kNN | ||
| CUMUL | ||
| k-FP (RF) | ||
| CNN (ours) |
| Configuration | Accuracy |
|---|---|
| CNN (ours), full order | |
| CNN, shuffled (padding fixed) | |
| best feature baseline (k-FP) | |
| CNN, input length 1000 | |
| CNN, input length 2000 | |
| CNN, input length 5000 |
Encrypted Network Traffic Analysis
Encrypted network traffic analysis infers applications, threats, and network conditions from traffic patterns without decrypting payloads.
See all 32 papers