Source Themes

RNN-Test: Towards adversarial testing for recurrent neural network systems

A general-purpose adversarial testing framework for seq2seq tasks in RNN systems, demonstrated its effectiveness over various tasks including language model, spell checker, speech recognition and image classification.

AdvDoor: Adversarial backdoor attack of deep learning system

Inject backdoor attacks with adversarial perturbations

Hdtest: Differential fuzz testing of brain-inspired hyperdimensional computing

Fuzz testing framework for brain-inspired hyperdimensional computing

Coverage Guided Differential Adversarial Testing of Deep Learning Systems

Comprehensive journal version of DLFuzz

Leopard: Identifying vulnerable code for vulnerability assessment through program metrics

Identify vulnerability-prone functions with program complexity analysis

Dlfuzz: Differential fuzzing testing of deep learning systems

The first fuzz testing framework in deep learning testing.

Cube-evo: A query-efficient black-box attack on video classification system

Query-efficient black-box attack for video classification