Skip to content

jadidbourbaki/permuted-partitioned-lbf

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

14 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Adversary Resilient Learned Bloom Filters

To work with the model, go to the model/ directory and run

make plot

To work with the permuted partitioned lbfs on the Malicious URLs dataset, go to src/ and run

python3 -m venv .venv
source .venv/bin/activate
pip3 install -r requirements.txt
python3 test_learning_model.py # does pre-processing
python3 experiments.py
python3 plot.py

To run the cuckoo filter experiments, run

python3 cuckoo_experiments.py
python3 cuckoo_plot.py

The experiments will generate the following files in the bin/ directory:

  • experiment_results.csv and plot_{classifier}.pdf for the original experiments
  • cuckoo_experiment_results.csv and cuckoo_plot_{classifier}.pdf for the cuckoo filter experiments

Based on AsiaCrypt 2025 reviewer feedback, we also added an extended set of experiments that check FPR when the memory budget takes on much larger values. To run this extended set of experiments, go to src/ and run

python3 -m venv .venv
source .venv/bin/activate
pip3 install -r requirements.txt
python3 test_learning_model.py # does pre-processing
python3 extended_experiments.py
python3 extended_plot.py
python3 extended_cuckoo_experiments.py
python3 extended_cuckoo_plot.py

About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published