Synthesizing Boxes Preconditions for Deep Neural Networks
This program is tentative and subject to change.
Deep neural network (DNN) has been increasingly deployed as a key component in safety-critical systems. However, the credibility of DNN components is uncertain due to the absence of formal specifications for their data preconditions, essential for ensuring trustworthy postconditions. In this paper, we propose a guess-and-check-based framework PreBoxes to automatically synthesize Boxes sufficient preconditions for DNN concerning rich safety and robustness postconditions. The guess phase effectively provides potentially non-trivial candidate sets and continuously reduces overhead throughout all designed heuristics. The check phase provides a provable guarantee. The entire framework supports automatic and adaptive iterative running to obtain weaker preconditions as well. Such resulting preconditions can be leveraged to shield DNN for safety and enhance the interpretability of DNN in application. PreBoxes has been evaluated on over 20 models with 23 trustworthy properties of 4 benchmarks and compared with 3 existing typical schemes. The results show that not only does PreBoxes generally infer weaker non-trivial sufficient preconditions for DNN than others, but also it expands competitive capabilities to deal with both complex properties and Non-ReLU complex structured networks.
This program is tentative and subject to change.
Wed 18 SepDisplayed time zone: Amsterdam, Berlin, Bern, Rome, Stockholm, Vienna change
13:30 - 14:50 | |||
13:30 20mTalk | NeuFair: Neural Network Fairness Repair with Dropout Technical Papers Vishnu Asutosh Dasu Pennsylvania State University, Ashish Kumar , Saeid Tizpaz-Niari University of Texas at El Paso, Gang Tan Pennsylvania State University | ||
13:50 20mTalk | A Large-Scale Empirical Study on Improving the Fairness of Image Classification Models Technical Papers Junjie Yang College of Intelligence and Computing, Tianjin University, Jiajun Jiang Tianjin University, Zeyu Sun Institute of Software, Chinese Academy of Sciences, Junjie Chen Tianjin University DOI | ||
14:10 20mTalk | Efficient DNN-Powered Software with Fair Sparse Models Technical Papers Xuanqi Gao Xi’an Jiaotong University, Weipeng Jiang Xi'an Jiaotong University, Juan Zhai University of Massachusetts, Amherst, Shiqing Ma University of Massachusetts, Amherst, Xiaoyu Zhang Xi'an Jiaotong University, Chao Shen Xi'an Jiaotong University Pre-print | ||
14:30 20mTalk | Synthesizing Boxes Preconditions for Deep Neural Networks Technical Papers Zengyu Liu College of Computer Science and Technology, National University of Defense Technology, Changsha 410073, China, Liqian Chen National University of Defense Technology, China, Wanwei Liu National University of Defense Technology, Ji Wang School of Computer, National University of Defense Technology, China |