Jul 2026· 2026 International Symposium on Machine Learning and Media Computing (MLMC)· pp. 1-7· 0 citations· 25 references
Abstract
To mitigate the vulnerability of deep neural networks in the face of adversarial attacks, a variety of defense strategies have been proposed in recent years. Adversarially robust distillation provides an effective approach by transferring knowledge from a robust teacher model to a student model. However, most existing robust distillation methods rely on a sufficiently robust teacher model, which is expensive to train in practice. This strong dependency greatly limits the practicality and scalability of robust distillation. To address this limitation, we propose an adversarially robust self-distillation (ARSD) method that does not require a robust teacher model as a training prerequisite. Starting from a standardly trained model, the proposed ARSD method guides adversarial training by leveraging the model’s own prediction. Besides, experimental results demonstrate that the performance of robust distillation is closely related to the divergence measure adopted in adversarial training. With reverse Jensen–Shannon divergence, the proposed ARSD method not only improves adversarial robustness, but also preserves a relatively high clean accuracy.
The obtained results exhibit the efficacy of the multi-teacher adversarial distillation and adaptive learning strategy, enhancing CNNs’ adversarial robustness against various adversarial attacks.
Hayat Ullah, Talha Zaidi, Arslan Munir· 0 citations
Adversarial training, one of the most effective methods for enhancing neural network robustness, is typically formulated as a min-max game between an attacker and a defender. Despite its success, most adversarial training methods suffer from robust overfitting, leading to a significant gap in robustness between the tra...
Xin-Yue Zhang, Shao-Cong Wu, Qiben Shan et al.· IEEE Transactions on Image P...· 0 citations
Among the evaluated models, CNNs exhibit the highest baseline robustness, whereas DNNs and RNNs rely more heavily on defense mechanisms to maintain performance, whereas DNNs and RNNs rely more heavily on defense mechanisms to maintain performance.
Surekha M., A. K. Sagar, Vineeta Khemchandani· International Journal of Int...· 0 citations
This work introduces Oscillatory Predictive Learning (OPL), a two-stage framework that combines Artificial Kuramoto Oscillatory Neurons (AKOrN) with predictive self-supervised pretraining using X-PhiNet and compares it with other randomized adversarial defense methods that provide precise, reproducible, and strong atta...
M. Habibi, Klea Ziu, Martin Takác et al.· 0 citations
Unrestricted Adversarial Examples (UAEs) pose a growing security challenge to Deep Neural Networks by introducing substantial, semantically natural modifications to images. While current diffusion-based methods improve the naturalness of UAEs, they suffer from two key limitations: an underutilization of the diffusion m...
Zhen-Zhao Pan, Xiao-Gang Zhang, Hua Chen et al.· IEEE Transactions on Pattern...· 0 citations
This work proposes Universal Continual Adversarial Defense (UCAD), a universal framework that enables both standard and robust models to perform effective defense under the CAD setting and observes that as the number of encountered attacks increases, UCAD becomes increasingly robust, consistently enhancing the defense...
Qian Wang, He-Fei Ling, Ying-Wei Li et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
