Skip to main content

Tools to encode PyTorch modules as Z3 constraints

Project description

Lantern: safer than a torch

Lantern is a software package to support SMT analysis of affine multiplexing neural networks using PyTorch and Z3.

See: docs/lantern/ for (generated) documentation.

See: requirements.txt for dependencies.

An annotated example.py demonstrates basic usage.

Lantern was developed against torch==1.5.0 and z3-solver==4.8.7.0. Linear Real Arithmetic appears to be stable, but we have noticed some changes to the floating point solvers as z3 continues to be developed.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

lantern-smt-0.1.0.tar.gz (4.0 kB view details)

Uploaded Source

File details

Details for the file lantern-smt-0.1.0.tar.gz.

File metadata

  • Download URL: lantern-smt-0.1.0.tar.gz
  • Upload date:
  • Size: 4.0 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/41.2.0 requests-toolbelt/0.9.1 tqdm/4.47.0 CPython/3.8.3

File hashes

Hashes for lantern-smt-0.1.0.tar.gz
Algorithm Hash digest
SHA256 7d2891ea864a79312d74a955e8360c90cddd50c7baa9f7206ef098e060493f22
MD5 52091c3901ce313bd1a0d82582fed590
BLAKE2b-256 00f86ff73d62527216b851991085be17a51077425e484e61b188d0a40a35c2df

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page