Jiajun Li
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Jiajun Li has a total of 8 co-authors. Here are the top co-authors by number of shared publications:
- Chao Huang
University of Southampton, UK
1 shared publication - Jiameng Fan
Boston University
1 shared publication - Qi Zhu
Northwestern University Evanston USA
1 shared publication - Weichao Zhou
Boston University
1 shared publication - Wenchao Li
School of Science, RMIT University, Melbourne, VIC 3001, Australia
1 shared publication - Xin Chen
University of New Mexico
1 shared publication
Latest Publications
- 8 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (3) , 994-1007
POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
Neural networks (NNs) playing the role of controllers have demonstrated impressive empirical performance on challenging control problems. However, the potential adoption of NN controllers in real-life applications has been significantly impeded by the growing concerns over the safety of these NN-controlled systems (NNCSs). In this work, we present POLAR-Express, an efficient and precise formal reachability analysis tool for verifying the safety of NNCSs. POLAR-Express uses Taylor model (TM) arithmetic to propagate TMs layer-by-layer across an NN to compute an overapproximation of the NN. It can be applied to analyze any feedforward NNs with continuous activation functions, such as ReLU, Sigmoid, and Tanh activation functions that cover the common benchmarks for NNCS reachability analysis. Compared with its earlier prototype POLAR, we develop a novel approach in POLAR-Express to propagate TMs more efficiently and precisely across ReLU activation functions, and provide parallel computation support for TM propagation, thus significantly improving the efficiency and scalability. Across the comparison with six other state-of-the-art tools on a diverse set of common benchmarks, POLAR-Express achieves the best verification efficiency and tightness in the reachable set analysis. POLAR-Express is publicly available at https://github.com/ChaoHuang2018/POLAR_Tool .
- 8 November 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
- Vol. 43 (3) , 994-1007
POLAR-Express: Efficient and Precise Formal Reachability Analysis of Neural-Network Controlled Systems
Neural networks (NNs) playing the role of controllers have demonstrated impressive empirical performance on challenging control problems. However, the potential adoption of NN controllers in real-life applications has been significantly impeded by the growing concerns over the safety of these NN-controlled systems (NNCSs). In this work, we present POLAR-Express, an efficient and precise formal reachability analysis tool for verifying the safety of NNCSs. POLAR-Express uses Taylor model (TM) arithmetic to propagate TMs layer-by-layer across an NN to compute an overapproximation of the NN. It can be applied to analyze any feedforward NNs with continuous activation functions, such as ReLU, Sigmoid, and Tanh activation functions that cover the common benchmarks for NNCS reachability analysis. Compared with its earlier prototype POLAR, we develop a novel approach in POLAR-Express to propagate TMs more efficiently and precisely across ReLU activation functions, and provide parallel computation support for TM propagation, thus significantly improving the efficiency and scalability. Across the comparison with six other state-of-the-art tools on a diverse set of common benchmarks, POLAR-Express achieves the best verification efficiency and tightness in the reachable set analysis. POLAR-Express is publicly available at https://github.com/ChaoHuang2018/POLAR_Tool .