Time-Efficient Evaluation and Enhancement of Adversarial Robustness in Deep Neural Networks
By: Runqi Lin
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.
Similar Papers
Algorithms for Adversarially Robust Deep Learning
Machine Learning (CS)
Makes AI safer from tricks and mistakes.
C-LEAD: Contrastive Learning for Enhanced Adversarial Defense
CV and Pattern Recognition
Makes AI smarter and harder to trick.
Towards Trustworthy Wi-Fi Sensing: Systematic Evaluation of Deep Learning Model Robustness to Adversarial Attacks
Machine Learning (CS)
Makes wireless sensing safer from hacking.