Abstract
背景:已有的方法(Muffin, Lemon, Cradle) can cover at most 34.1% layer inputs, 25.9% layer parameter values, and 15.6% layer sequences.
本文:COMET
Github: https://github.com/maybeLee/COMET
Bug Type: Crash, NaN, inconsistency between the TensorFlow library and the ONNXRuntime library
Task: fuzzing API of DL Libraries
Method:
- designs a set of mutation operators and a coverage-based search algorithm to diversify layer inputs, layer parameter values, and layer sequences in DL models
- model synthesis
实验:
对象:ONNXRuntime, MXNet, Keras-MXNet, TF2ONNX, ONNX2PyTorch, Keras, TensorFlow, PyTorch
Competitors: Muffin, Lemon, Cradle
效果:
- +32 bugs, 21 confirmed, 7 fixed