Artifacts for Bytecode Classification

Artifact release for CCS 2023 submission entitled "Read Between the Lines: Detecting Tracking JavaScript with Bytecode Classification".

• Data for comparison study (Section 5.2) can be found at:
  • D1
  • D2
  • D3
• Vectorized dataset for random forest can be found here
• Due to size, the data for the training and testing DPCNN and FastText models (Section 5) is available upon request.
• The evaluation code for each model as well as the comparison study can be found under code/

• Filter lists rules and Tranco top 1 Million website files can be found under lists/
• We only included one version of enhancedstats.txt since its content did not change.