Time-Efficient Evaluation and Enhancement of Adversarial Robustness in Deep Neural Networks
This work aims to improve the safety of DNNs in real-world applications by reducing computational costs, though it appears incremental as it builds on existing red-blue adversarial frameworks.
The paper tackles the problem of computationally intensive adversarial robustness evaluation and enhancement in deep neural networks, proposing time-efficient methods to address this limitation.
With deep neural networks (DNNs) increasingly embedded in modern society, ensuring their safety has become a critical and urgent issue. In response, substantial efforts have been dedicated to the red-blue adversarial framework, where the red team focuses on identifying vulnerabilities in DNNs and the blue team on mitigating them. However, existing approaches from both teams remain computationally intensive, constraining their applicability to large-scale models. To overcome this limitation, this thesis endeavours to provide time-efficient methods for the evaluation and enhancement of adversarial robustness in DNNs.