DeepGauge: multi-granularity testing criteria for deep learning systems
ASE, pp. 120-131, 2018.
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulne...More
Full Text (Upload PDF)
PPT (Upload PPT)
Best Paper of ASE, 2018