Understanding Local Robustness of Deep Neural Networks under Natural Variations

Understand

Deep Neural Networks (DNNs) are being deployed in a wide range of settings today, from safety-critical applications like autonomous driving to commercial applications involving image classifications.

• However, recent research has shown that DNNs can be brittle to even slight variations of the input data.
• Therefore, rigorous testing of DNNs has gained widespread attention.
• While DNN robustness under norm-bound perturbation got significant attention over the past few years, our knowledge is still limited when natural variants of the input images come.