testingautomated-usi Goto Github PK

adversarial-rl-icst-2024

Replication package for the paper "Adversarial Testing with Reinforcement Learning: A Case Study on Autonomous Driving"

ambguess-src

ambiguous-datasets

bisupervised

TOSEM paper replication package

corrupted-text

A python library to generate out-of-distribution text datasets. Specifically, the library applies model-independent, commonplace corruptions (not model-specific, worst-case adversarial corruptions). We thus aim to allow benchmark-studies regarding robustness against realistic outliers.

deepatash

focused test generation for DL systems

deephyperion

deepjanus

Tools and data of the paper "Model-based Exploration of the Frontier of Behaviours for Deep Learning System Testing"

deepmetis

deepthoughts

dnn-tip

A collection of dnn test input prioritizers often used as benchmarks in recent literature.

fashion-mnist-c

genbo

Replication package for the paper "Boundary State Generation for Testing and Improvement of Autonomous Driving Systems"

jsep2021-replication-package-material

maxitwo

Replication package of the paper "Two is Better Than One: Digital Siblings to Improve Autonomous Driving Testing"

repli-ensemble-bench

repli-icst2021-uncertainty

Source Code of the ICST 2021 paper "Fail-Safe Execution of Deep Learning based Systems through Uncertainty"

repli-stvr2022-uncertainty

rl-plasticity-experiments

Source code and data for the paper "Testing the Plasticity of Reinforcement Learning Based Systems"

selforacle

The code of our paper "Misbehaviour Prediction for Autonomous Driving Systems", including our improved Udacity simulator

simple-tip

This is the reproduction package of the paper Simple Techniques Work Surprisingly Well for Neural Network Test Prioritization and Active Learning by M.Weiss and P.Tonella, published at ISSTA 2022

surprise-adequacy

tig-validity-icse23

unboxer

An Empirical Study on Low- and High-Level Explanations of Deep Learning Misbehaviours

uncertainty-wizard

Uncertainty-Wizard is a plugin on top of tensorflow.keras, allowing to easily and efficiently create uncertainty-aware deep neural networks. Also useful if you want to train multiple small models in parallel.

urop-2021-exercise

Repository for UROP 2021 exercise