← Search

Jialei Song

2 accepted papers

2025

RDI: An adversarial robustness evaluation metric for deep neural networks based on model statistical features

UAI 2025

Deep neural networks (DNNs) are highly susceptible to adversarial samples, raising concerns about their reliability in safety-critical tasks. Currently, methods of evaluating adversarial robustness are primarily categorized into attack-based and certified robustness evaluation approaches. The former

2018

Toward a Transform Method From Lighthill Fish Swimming Model to Biomimetic Robot Fish

RA-L 2018

How to build a biomimetic robot fish has always been a divergent question. Most of the existing robot fishes suffer structural complexity and propulsive inefficiency. In this paper, we proposed a method that transfers the natural actuation properties of fish to the biomimetic robot counterpart. The

Cited by 38SourceScholar