no code implementations • 25 Feb 2022 • Shucen Ma, Jianqi Shi, Yanhong Huang, Shengchao Qin, Zhe Hou
The broad adoption of Machine Learning (ML) in security-critical fields demands the explainability of the approach.
no code implementations • 19 Sep 2020 • Liming Zhai, Felix Juefei-Xu, Qing Guo, Xiaofei Xie, Lei Ma, Wei Feng, Shengchao Qin, Yang Liu
To defend the DNNs from the negative rain effect, we also present a defensive deraining strategy, for which we design an adversarial rain augmentation that uses mixed adversarial rain layers to enhance deraining models for downstream DNN perception.
no code implementations • 19 Sep 2020 • Binyu Tian, Qing Guo, Felix Juefei-Xu, Wen Le Chan, Yupeng Cheng, Xiaohong Li, Xiaofei Xie, Shengchao Qin
Our method reveals the potential threat to the DNN-based X-ray automated diagnosis and can definitely benefit the development of bias-field-robust automated diagnosis system.
no code implementations • 12 Dec 2017 • Jingyi Wang, Jun Sun, Yifan Jia, Shengchao Qin, Zhiwu Xu
As the system is too complicated to be manually modeled, we apply latest automatic model learning techniques to construct a set of Markov chains through abstraction and refinement, based on two long system execution logs (one for training and the other for testing).
2 code implementations • 20 Oct 2016 • Jingyi Wang, Jun Sun, Shengchao Qin, Cyrille Jegourel
The other is a probabilistic model based on which the given property is `verified'.
Software Engineering