Firstly, the previous definitions of robustness in trajectory prediction are ambiguous.
Moreover, based on the framework, we propose the multi-objective DNN repair problem and give an algorithm based on our incremental SMT solving algorithm.
The safety properties proved in the resulting surrogate model apply to the original ADS with a probabilistic guarantee.
In this paper, we propose a framework of filter-based ensemble of deep neuralnetworks (DNNs) to defend against adversarial attacks.
It is shown that DeepPAC outperforms the state-of-the-art statistical method PROVERO, and it achieves more practical robustness analysis than the formal verification tool ERAN.
The core idea is to make use of the obtained constraints of the abstraction to infer new bounds for the neurons.