DeepAI AI Chat
Log In Sign Up

secml: A Python Library for Secure and Explainable Machine Learning

12/20/2019
by   Marco Melis, et al.
Universita Cagliari
122

We present secml, an open-source Python library for secure and explainable machine learning. It implements the most popular attacks against machine learning, including not only test-time evasion attacks to generate adversarial examples against deep neural networks, but also training-time poisoning attacks against support vector machines and many other algorithms. These attacks enable evaluating the security of learning algorithms and of the corresponding defenses under both white-box and black-box threat models. To this end, secml provides built-in functions to compute security evaluation curves, showing how quickly classification performance decreases against increasing adversarial perturbations of the input data. secml also includes explainability methods to help understand why adversarial attacks succeed against a given model, by visualizing the most influential features and training prototypes contributing to each decision. It is distributed under the Apache License 2.0, and hosted at https://gitlab.com/secml/secml.

READ FULL TEXT
02/08/2017

Adversarial Attacks on Neural Network Policies

Machine learning classifiers are known to be vulnerable to inputs malici...
09/05/2018

Bridging machine learning and cryptography in defence against adversarial attacks

In the last decade, deep learning algorithms have become very popular th...
01/02/2020

Ensembles of Many Diverse Weak Defenses can be Strong: Defending Deep Neural Networks Against Adversarial Attacks

Despite achieving state-of-the-art performance across many domains, mach...
03/26/2021

MagDR: Mask-guided Detection and Reconstruction for Defending Deepfakes

Deepfakes raised serious concerns on the authenticity of visual contents...
07/29/2020

End-to-End Adversarial White Box Attacks on Music Instrument Classification

Small adversarial perturbations of input data are able to drastically ch...
03/08/2020

Security of Distributed Machine Learning: A Game-Theoretic Approach to Design Secure DSVM

Distributed machine learning algorithms play a significant role in proce...
02/07/2018

A Game-Theoretic Approach to Design Secure and Resilient Distributed Support Vector Machines

Distributed Support Vector Machines (DSVM) have been developed to solve ...

Code Repositories

secml

A Python library for Secure and Explainable Machine Learning


view repo