1. Poster
- Author
-
Leo Hyun Park, Jaeuk Kim, Taekyoung Kwon, Sang-Jin Oh, and Soochang Chung
- Subjects
Computer science ,business.industry ,Deep learning ,02 engineering and technology ,Fuzz testing ,computer.software_genre ,Machine learning ,0202 electrical engineering, electronic engineering, information engineering ,Deep neural networks ,020201 artificial intelligence & image processing ,Compiler ,Artificial intelligence ,Layer (object-oriented design) ,business ,computer ,Interpretability - Abstract
Deep neural networks (DNNs) gained in popularity as an effective machine learning algorithm, but their high complexity leads to the lack of model interpretability and difficulty in the verification of deep learning. Fuzzing, which is an automated software testing technique, is recently applied to DNNs as an effort to address these problems by following the trend of coverage-based fuzzing. However, new coverage metrics on DNNs may bring out the question of which layer to measure the coverage in DNNs. In this poster, we empirically evaluate the performance of existing coverage metrics. By the comparative analysis of experimental results, we compile the most effective layer for each of coverage metrics and discuss a future direction of DNN fuzzing.
- Published
- 2019
- Full Text
- View/download PDF