A certifiable defense against adversarial examples by training neural networks to be provably robust
-
Updated
Jan 13, 2021 - Python
A certifiable defense against adversarial examples by training neural networks to be provably robust
MIRROR of https://codeberg.org/catseye/SixtyPical : A 6502-oriented low-level programming language supporting advanced static analysis
🎯 soap - Structural Optimisation of Arithmetic Programs
Python library for building embedded languages within Python that have alternative operational semantics and abstract interpretations.
Abstract Neural Networks (SAS 2020)
Reference implementations for Symbolic Abstraction algorithms.
Experimental python linter/interpreter intended to check tensor/matrix/arrays operations using NumPy (currently only works in Python 3.6 and Python 3.7)
pyApron: A library for numerical abstract domains manipulation based on Apron
Pointer Analysis of CPython Bytecode using Abstract Interpretation
Add a description, image, and links to the abstract-interpretation topic page so that developers can more easily learn about it.
To associate your repository with the abstract-interpretation topic, visit your repo's landing page and select "manage topics."