Trustworthy Machine Learning


A suite of tools for making machine learning secure and trustworthy

The website http://TrustworthyMachineLearning.org/ introduces updates of a suite of tools we have designed for making machine learning secure and trustworthy. This project involves toolboxes for five main tasks (organized as entries in the navigation menu). Feel free to submit pull requests when you find my typos.


Scope of problems our tools aim to tackle

Classifiers based on machine learning algorithms have shown promising results for many security tasks including malware classification and network intrusion detection, but classic machine learning algorithms are not designed to operate in the presence of adversaries. Intelligent and adaptive adversaries may actively manipulate the information they present in attempts to evade a trained classifier, leading to a competition between the designers of learning systems and attackers who wish to evade them. This project is developing automated techniques for predicting how well classifiers will resist the evasions of adversaries, along with general methods to automatically harden machine-learning classifiers against adversarial evasion attacks.

Five important tasks

At the junction between machine learning and computer security, this project involves toolboxes for five main task as shown in the following table. Our system aims to allow a classifier designer to understand how the classification performance of a model degrades under evasion attacks, enabling better-informed and more secure design choices. The framework is general and scalable, and takes advantage of the latest advances in machine learning and computer security.

timeline

timeline

No. Tool Category ~~~~~~~Paper~Title~~~~ Venues Software
1 Evade Machine Learning Automatically Evading Classifiers, Case Study on PDF Malware Classifiers NDSS16 GitHub
2 Evade Machine Learning Black-box Generation of Adversarial Text Sequences to Fool Deep Learning Classifiers DeepSecureWkp18 GitHub
3 Detect Adversarial Attacks Feature Squeezing- Detecting Adversarial Examples in Deep Neural Networks NDSS18 GitHub
4 Defense against Adversarial Attacks DeepCloak- Masking Deep Neural Network Models for Robustness against Adversarial Samples ICLRwkp17 GitHub
5 Visualize Adversarial Attacks Adversarial-Playground- A Visualization Suite for Adversarial Samples VizSec17 GitHub
6 Theorems of Adversarial Examples A Theoretical Framework for Robustness of (Deep) Classifiers Against Adversarial Samples ICLRwkp17  

Contact

Have questions or suggestions? Feel free to ask me on Twitter or email me.

Thanks for reading!