F3arwin -

[2] Goodfellow, I. J., Shlens, J., & Szegedy, C. (2015). Explaining and harnessing adversarial examples. ICLR .

[4] Madry, A., Makelov, A., Schmidt, L., Tsipras, D., & Vladu, A. (2018). Towards deep learning models resistant to adversarial attacks. ICLR . f3arwin

[5] Su, J., Vargas, D. V., & Sakurai, K. (2018). One pixel attack for fooling deep neural networks. IEEE Transactions on Evolutionary Computation . [2] Goodfellow, I

f3arwin significantly outperforms prior genetic attacks due to adaptive mutation and SBX crossover, which preserves high-fitness perturbation structures. Compared to Square Attack, f3arwin requires 11% fewer queries for a similar ASR. On VGG-16 (unseen during attack generation), f3arwin perturbations crafted on ResNet-50 achieved 68.3% ASR, vs. 51.2% for Square Attack and 59.7% for standard genetic attack. This suggests that evolutionary perturbations capture more model-agnostic features. 5.3 Defensive Robustness | Defense Method | Clean Acc. | Robust Acc. (PGD) | Robust Acc. (f3arwin attack) | |----------------|------------|------------------|-------------------------------| | Standard | 92.1% | 0.3% | 0.1% | | PGD-AT | 88.4% | 51.2% | 43.5% | | TRADES | 87.9% | 53.1% | 46.2% | | f3arwin defense | 89.2% | 54.8% | 58.9% | Explaining and harnessing adversarial examples

$$F(\delta) = \underbrace\mathbbI[f_\theta(x+\delta) \neq y] \cdot (1 - \textsoftmax(f_\theta(x+\delta)) y) \textMisclassification confidence - \lambda \cdot \frac\delta\epsilon \sqrtd$$

[6] Zhang, H., Yu, Y., Jiao, J., Xing, E. P., Ghaoui, L. E., & Jordan, M. I. (2019). Theoretically principled trade-off between robustness and accuracy. ICML .