Posts
Welcome to the cleverhans blog
This is a blog by Ian Goodfellow and Nicolas Papernot about security and privacy in machine learning.
-
If you came here looking for the open-source
cleverhans
library for benchmarking the vulnerability of machine learning models to adversarial examples, here is its GitHub repository. -
If you were looking for the technical report associated with the
cleverhans
library, it is available here and the BibTex entry for it is:
@article{papernot2016cleverhans,
title={cleverhans v1.0.0: an adversarial machine learning library},
author={Papernot, Nicolas and Goodfellow, Ian and Sheatsley, Ryan and Feinman, Reuben and McDaniel, Patrick},
journal={arXiv preprint arXiv:1610.00768},
year={2016}
}
Here is a list of all entries in our blog.
-
How to prompt LLMs with private data?
-
Can stochastic pre-processing defenses protect your models?
-
Are adversarial examples against proof-of-learning adversarial?
-
How to Keep a Model Stealing Adversary Busy?
-
All You Need Is Matplotlib
-
Arbitrating the integrity of stochastic gradient descent with proof-of-learning
-
Beyond federation: collaborating in ML with confidentiality and privacy
-
Is this model mine?
-
To guarantee privacy, focus on the algorithms, not the data
-
Teaching Machines to Unlearn
-
In Model Extraction, Don’t Just Ask ‘How?’: Ask ‘Why?’
-
How to steal modern NLP systems with gibberish?
-
How to know when machine learning does not know
-
Machine Learning with Differential Privacy in TensorFlow
-
Privacy and machine learning: two unexpected allies?
-
The challenge of verification and testing of machine learning
-
Is attacking machine learning easier than defending it?
-
Breaking things is easy
subscribe via RSS