The robustness of Deep Neural Networks (DNNs) against adversarial attacks is an important topic in the area of deep learning. To fully investigate the robustness of DNNs, this study examines four frequently used white box adversarial attack techniques, namely, the Fast Gradient Sign Method (FGSM), Projected Gradient Descent (PGD), Basic Iterative Method (BIM), DeepFool, and their effects on DNN models for the image classification task. The results show that ResNet152 and DenseNet201 are less vulnerable comparing to other DNN models to a variety of individual attacks, highlighting their intrinsic strength even in the lack of specific adversarial training. Further, we propose two ensemble adversarial attacks combining three individual attacks for generating adversarial examples from the tiny ImageNet, CIFAR-10, CIFAR-100, and SVHN datasets for DNN model evaluation. It is observed that the performance of the DNNs deteriorate significantly under the proposed ensemble adversarial attacks even after defensive measures have been applied. For instance, the accuracy of the most robust DNN that we tested, namely the defense distillation enhanced DenseNet201, dropped more than 59% under the proposed ensemble adversarial attacks, comparing to only 34% decrease under the individual attacks.

Reliable pore detection in in situ monitoring is essential for quality control in additive manufacturing, particularly in safety-critical applications. However, existing automated approaches often struggle with low-quality images, computational inefficiency, and the lack of reliable uncertainty estimates to identify the pores accurately. To address these limitations, this paper proposes U-SAMNet, an Uncertainty-Aware Self-Attention Multi-Task Network. The model jointly performs pore segmentation, image-level classification, and denoising on in situ monitoring images, while deriving epistemic uncertainty via Monte Carlo dropout variance to dynamically suppress unreliable attention features. This study uses electron-optical (ELO) images from the E-PBF process. A novel Uncertainty Guidance Attention (UGA) block is introduced. It suppresses channel attention weights using inverted uncertainty estimates. Unlike prior methods that modulate classification weights, U-SAMNet operates on pixel-wise feature maps. The model has only 1.69 M parameters. A single forward pass takes 17.46 ms per image, while uncertainty estimation is performed through multiple Monte Carlo dropout passes. The model was evaluated on real E-PBF images and achieved 99.42% pixel accuracy, 85.31% F1-score, and 74.38% IoU on a held-out test set of 43 real images. It also generalizes to other industrial defect detection benchmarks, reaching 85.09% F1-score on DAGM 2007 and 82.32% on DeepCrack. GAN-synthesized training data improves the F1-score by 21.34 percentage points over rotation augmentation alone. Ablation studies confirm that each component contributes meaningfully to the final performance.

Bayesian Neural Networks (BNNs) are increasingly used in bioinformatics to manage challenges related to breaking down large, high-dimensional biological datasets and modeling complex biological processes. Our research employs BNNs to uncover and understand the fundamental phenotypic characteristics immersed in seal DNA methylation (DNAm) data. Methylation of DNA is an epigenetic process in which a methyl group is attached to cytosine in the CpG motif, altering gene expression without changing the underlying DNA sequence. We explored DNAm patterns using BNN models in three pinniped species (northern elephant seal, Mirounga angustirostris; Hawaiian monk seal, Neomonachus schauinslandii; Weddell seal, Leptonychotes weddellii). Our BNN model correctly classifies individuals into species based on their unique methylation profiles with perfect accuracy, demonstrating the dramatic divergence in methylation patterns across species as well as the power of our model. Furthermore, our BNNs use the same methylation data to distinguish muscle and skin tissue types for the northern elephant seal samples. This is a critical feature as epigenetic regulatory patterns are expected to differ across tissue types, underscoring how tissues can be differentially controlled at the epigenetic level. In addition, our highly accurate model can be more broadly useful to understand tissue-specific epigenetic variation with respect to phenotypic traits in other species.