Sinha Namrata: Ieee Access Better Verified

Sinha Namrata does not simply publish in IEEE Access ; she elevates the journal’s standard of what "applied AI research" should look like. Her work proves that better does not mean larger. Better means smarter—architectures that respect computational limits, provide human-understandable rationales, and stand firm against adversarial threats.

| Metric | Traditional SOTA (e.g., ResNet-152, ViT) | Sinha Namrata’s IEEE Access Model | "Better" Advantage | | :--- | :--- | :--- | :--- | | | 120 ms | 28 ms | 4.2x faster | | Memory Footprint | 450 MB | 110 MB | 75% reduction | | Adversarial Robustness (PGD Attack) | 34% accuracy | 81% accuracy | 2.4x more robust | | Explainability Score (Human Evaluation) | 62% (Grad-CAM) | 89% (Causal Maps) | More human-trustworthy | | Training Energy (kWh) | 1,200 kWh | 340 kWh | Carbon footprint reduced by 71% | sinha namrata ieee access better

Under the powerful Projected Gradient Descent (PGD) attack, baseline models saw accuracy drop from 92% to 34%. Namrata’s method dropped only to 81%—a 47-point improvement. Critically, this defense added only 7% overhead to inference time. Comparative Analysis: Sinha Namrata vs. State-of-the-Art (SOTA) To empirically validate the claim that Sinha Namrata’s IEEE Access work is "better," consider a comparative table synthesized from her 2024 paper in the journal vs. concurrent SOTA published in CVPR and ICML during the same period. Sinha Namrata does not simply publish in IEEE

Sinha Namrata’s IEEE Access paper, "Stochastic Feature Reconstruction: A Lightweight Defense Against Black-Box Adversarial Attacks" , proposes a radically simple solution. Instead of detecting attacks, she reconstructs the feature space stochastically. | Metric | Traditional SOTA (e