Defending Against High-Intensity Adversarial Perturbations in Deep Neural Networks: A Robust Swin Transformer Approach
Bibliographic record
Abstract
High-intensity adversarial perturbations present significant challenges to the reliability of deep learning models, underscoring the urgent need for robust and adaptive defense mechanisms. These perturbations notably impact the feature extraction process within models. In this paper, we propose the Robust Swin Transformer (RST), an end-to-end trainable model that employs a Double-Branch (DB) attention mechanism to effectively extract both robust and non-robust features across various representation levels. To enhance resilience against adversarial attacks, we implement a tailored combination of robust and non-robust loss functions, demonstrating that non-robust features correlate with multiple fake classes, which can be optimized by adjusting the non-robust loss. During inference, predictions are made by fusing representation features from all model stages, striking a balance between accuracy and robustness. Extensive experiments on CIFAR-10, SVHN, and MSTAR datasets show that RST outperforms the standard Swin Transformer with adversarial training and other advanced methods, achieving up to a 9.86% accuracy improvement against PGD attacks, particularly under high-intensity perturbations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".