fingerprint-securedrop
fingerprint-securedrop copied to clipboard
A machine learning data analysis pipeline for analyzing website fingerprinting attacks and defenses.
We should implement open-world cross-validation - and the ability to define how much of the world the adversary can see. Both these config options (`world: type: 'open'` and `world: observed_fraction`)...
If you try to import `matplotlib.pyplot` in the REPL without it you get errors.
Moving [this](https://github.com/freedomofpress/fingerprint-securedrop/blob/master/fpsd/classify.py#L120) `if` statement that performs feature scaling outside the fold loop it's in would save some minor computation time.
`stem` has this capability, and it would be useful to expose via the configfile because @mikeperry-tor is interested in using this repo to test his adaptive padding prototype, where padding...
_Edit: see https://github.com/freedomofpress/FingerprintSecureDrop/issues/4#issuecomment-228825080 for a better explanation and traceback. Don't know why this original report was so half-assed and lacked even the full traceback._ So the crawler is for the...
See https://github.com/webfp/tor-browser-crawler/pull/32
We want to know in a realistic scenario - i.e. one that incorporates the effect of the class imbalance - how effective these attacks are in terms of true and...
Reading of some recent Tor logs suggestions it might not be. Also, make sure that the code in the crawler is correctly identifying what the client's guard fingerprint actually is.
It would be nice to make sure that if someone wants to use our tools as a package they can do so with expected results, while at the same time...