Synthetic network generators preserve cross-flow correlations enabling source-level membership inference, shown via the TraceBleed attack across five datasets and six generators.
Netdiffusion: Network data augmentation through protocol-constrained traffic generation
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
SATA generates realistic new traffic patterns absent from training data and boosts open-world website fingerprinting accuracy by 90.81% and AUROC by 48.37% through protocol-based semantic augmentation and cross-layer feature alignment.
citing papers explorer
-
Cross-Flow Correlations Survive Synthesis: Measuring Source-Level Privacy Leakage in Synthetic Network Traces
Synthetic network generators preserve cross-flow correlations enabling source-level membership inference, shown via the TraceBleed attack across five datasets and six generators.
-
More Than Meets the Eye: A Semantics-Aware Traffic Augmentation Framework for Generalizable Website Fingerprinting
SATA generates realistic new traffic patterns absent from training data and boosts open-world website fingerprinting accuracy by 90.81% and AUROC by 48.37% through protocol-based semantic augmentation and cross-layer feature alignment.