Time-Efficient Evaluation and Enhancement of Adversarial Robustness in Deep Neural Networks
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). First posted on arXiv 24 Dec 2025.
Builds on
0 of 0 references.
No references here yet.
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2020Towards Robust Neural Networks via Orthogonal Diversity
- 2022Towards Alternative Techniques for Improving Adversarial Robustness: Analysis of Adversarial Training at a Spectrum of Perturbations
- 2023ARBiBench: Benchmarking Adversarial Robustness of Binarized Neural Networks
- 2022Improving Robustness by Enhancing Weak Subnets
- 2024Exploring Adversarial Robustness of Deep State Space Models
- 2022Pruning Adversarially Robust Neural Networks without Adversarial Examples
- 2025Trading Inference-Time Compute for Adversarial Robustness
- 2026Fast Adversarial Attacks with Gradient Prediction