ZK-APEX: Zero-Knowledge Approximate Personalized Unlearning with Executable Proofs

The empirical evaluation of Frank-Wolfe methods for constructing white-box adversarial attacks highlights the need for efficient adversarial attack construction in neural networks, particularly focusing on numerical optimization techniques. The study emphasizes the application of modified Frank-Wolfe methods to enhance the robustness of neural networks against adversarial threats, utilizing datasets like MNIST and CIFAR-10 for testing.

A recent study has introduced a hierarchical attention model for detecting sparse volumetric anomalies in subclinical keratoconus using three-dimensional anterior segment optical coherence tomography (AS-OCT). This model outperformed traditional convolutional neural networks (CNNs) and global-attention Vision Transformers (ViTs) by achieving 21-23% higher sensitivity and specificity in identifying subtle abnormalities.

A new hybrid architecture named TranSamba has been proposed for weakly supervised volumetric medical segmentation, integrating a Vision Transformer backbone with Cross-Plane Mamba blocks. This design aims to enhance the model's ability to capture 3D context, improving object localization in volumetric medical imaging while maintaining efficient memory usage and linear time complexity with respect to input volume depth.

A new study has developed an optimized deep learning pipeline for automated fish re-identification using the AutoFish dataset, which simulates Electronic Monitoring systems with conveyor belts featuring six similar fish species. The research demonstrates significant improvements in key metrics, achieving a peak performance of 41.65% mAP@k and 90.43% Rank-1 accuracy through advanced techniques like hard triplet mining and a custom image transformation pipeline.