A Two-Phase Evolutionary Framework to Boost Adversarial Robustness in Neural Networks
Bibliographic record
Abstract
Deep neural networks (DNNs) achieve remarkable performance in machine learning, but are vulnerable to adversarial attacks, such as those generated by Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD), which induce misclassifications, endangering safety-critical applications like autonomous driving, medical diagnostics, and cybersecurity. This study proposes a two-phase training framework to enhance adversarial robustness without sacrificing accuracy. The initial phase establishes baseline performance, while the adaptive phase iteratively evolves the dataset by incorporating adversarial synthetic data generated via FGSM and PGD, targeting model vulnerabilities through cycles of training, evaluation, and dataset augmentation. Evaluated on the Modified National Institute of Standards and Technology database (MNIST, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 0, 0 0 0}$</tex> samples), the Canadian Institute For Advanced Research 10-class dataset (CIFAR-10, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 0, 0 0 0}$</tex> samples), BrainTumor-7K (7,023 MRIs), and the Phishing Legitimate Dataset (Phishing, <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$\mathbf{1 0, 0 0 0}$</tex> samples), this framework yields significant robustness gains against FGSM and PGD attacks: 73.73 % on MNIST <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$(92.71 \pm 0.32 \%$</tex> vs. <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$18.98 \pm 0.45 \%$</tex> adversarial accuracy), 7.17 % on CIFAR-10 (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$41.04 \pm 0.37 \%$</tex> vs. <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$33.87 \pm 0.41 \%$</tex>), 73.22 % on BrainTumor-7K (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$89.60 \pm 0.33 \%$</tex> vs. <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$16.38 \pm 0.42 \%$</tex>), and 20.85 % on Phishing (<tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$94.10 \pm 0.22 \%$</tex> vs. <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$73.25 \pm 0.38 \%$</tex>). Furthermore, clean accuracy improves (e.g., 0.20 % MNIST, 3.12 % CIFAR-10), challenging the robustness-accuracy trade-off. This framework provides a scalable and efficient solution for resilient AI, preserving innovative methods for future intellectual property protection in cybersecurity and medical imaging applications
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 | 0.002 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.008 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.004 | 0.005 |
| Research integrity | 0.001 | 0.003 |
| Insufficient payload (model declined to judge) | 0.001 | 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".