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.
|Title of host publication||CCS 2019 - Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security|
|Publisher||Association for Computing Machinery|
|Number of pages||3|
|Publication status||Published - 2019 Nov 6|
|Event||26th ACM SIGSAC Conference on Computer and Communications Security, CCS 2019 - London, United Kingdom|
Duration: 2019 Nov 11 → 2019 Nov 15
|Name||Proceedings of the ACM Conference on Computer and Communications Security|
|Conference||26th ACM SIGSAC Conference on Computer and Communications Security, CCS 2019|
|Period||19/11/11 → 19/11/15|
Bibliographical noteFunding Information:
This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korea government (MSIT) (No. NRF-2019R1A2C1088802).
© 2019 Association for Computing Machinery.
All Science Journal Classification (ASJC) codes
- Computer Networks and Communications