Deep Neural Networks (DNNs) have been used to solve different day-to-day
problems. Recently, DNNs have been deployed in real-time systems, and lowering
the energy consumption and response time has become the need of the hour. To
address this scenario, researchers have proposed incorporating dynamic
mechanism to static DNNs (SDNN) to create Dynamic Neural Networks (DyNNs)
performing dynamic amounts of computation based on the input complexity.
Although incorporating dynamic mechanism into SDNNs would be preferable in
real-time systems, it also becomes important to evaluate how the introduction
of dynamic mechanism impacts the robustness of the models. However, there has
not been a significant number of works focusing on the robustness trade-off
between SDNNs and DyNNs. To address this issue, we propose to investigate the
robustness of dynamic mechanism in DyNNs and how dynamic mechanism design
impacts the robustness of DyNNs. For that purpose, we evaluate three research
questions. These evaluations are performed on three models and two datasets.
Through the studies, we find that attack transferability from DyNNs to SDNNs is
higher than attack transferability from SDNNs to DyNNs. Also, we find that
DyNNs can be used to generate adversarial samples more efficiently than SDNNs.
Then, through research studies, we provide insight into the design choices that
can increase robustness of DyNNs against the attack generated using static
model. Finally, we propose a novel attack to understand the additional attack
surface introduced by the dynamic mechanism and provide design choices to
improve robustness against the attack.

通过对三个模型和两个数据集进行评估，我们发现从 DyNNs 到 SDNNs 的攻击传递性高于从 SDNNs 到 DyNNs 的攻击传递性，以及 DyNNs 可以更高效地生成对抗样本。然后，通过研究，我们提供了增强 DyNNs 对静态模型生成的攻击的鲁棒性的设计选择的见解，并提出了一种新的攻击方法来理解动态机制引入的额外攻击面并提供提高抵抗攻击的设计选择。