4 citations · 9 across the 10 of their papers we have counts for
10 papers
Verifying Safety of Neural Networks from Topological Perspectives
Zhen Liang, Dejin Ren, Bai Xue +3
Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their beha…
Model Predictive Control with Reach-avoid Analysis
Dejin Ren, Wanli Lu, Jidong Lv +2
In this paper we investigate the optimal controller synthesis problem, so that the system under the controller can reach a specified target set while satisfying given constraints.…
Repairing Deep Neural Networks Based on Behavior Imitation
Zhen Liang, Taoran Wu, Changyuan Zhao +4
The increasing use of deep neural networks (DNNs) in safety-critical systems has raised concerns about their potential for exhibiting ill-behaviors. While DNN verification and test…
Provable Reach-avoid Controllers Synthesis Based on Inner-approximating Controlled Reach-avoid Sets
Jianqiang Ding, Taoran Wu, Yuping Qian +2
In this paper, we propose an approach for synthesizing provable reach-avoid controllers, which drive a deterministic system operating in an unknown environment to safely reach a de…
Scenario Approach for Parametric Markov Models
Ying Liu, Andrea Turrini, Moritz Hahn +2
In this paper, we propose an approximating framework for analyzing parametric Markov models. Instead of computing complex rational functions encoding the reachability probability a…
Credit Assignment for Trained Neural Networks Based on Koopman Operator Theory
Zhen Liang, Changyuan Zhao, Wanwei Liu +3
Credit assignment problem of neural networks refers to evaluating the credit of each network component to the final outputs. For an untrained neural network, approaches to tackling…
Safety Verification for Neural Networks Based on Set-boundary Analysis
Zhen Liang, Dejin Ren, Wanwei Liu +3
Neural networks (NNs) are increasingly applied in safety-critical systems such as autonomous vehicles. However, they are fragile and are often ill-behaved. Consequently, their beha…
Ensemble Defense with Data Diversity: Weak Correlation Implies Strong Robustness
Renjue Li, Hanwei Zhang, Pengfei Yang +4
In this paper, we propose a framework of filter-based ensemble of deep neuralnetworks (DNNs) to defend against adversarial attacks. The framework builds an ensemble of sub-models -…
Towards Practical Robustness Analysis for DNNs based on PAC-Model Learning
Renjue Li, Pengfei Yang, Cheng-Chao Huang +3
To analyse local robustness properties of deep neural networks (DNNs), we present a practical framework from a model learning perspective. Based on black-box model learning with sc…
Improving Neural Network Verification through Spurious Region Guided Refinement
Pengfei Yang, Renjue Li, Jianlin Li +5
We propose a spurious region guided refinement approach for robustness verification of deep neural networks. Our method starts with applying the DeepPoly abstract domain to analyze…