Deep learning models have become central to many computer vision tasks, yet their vulnerability to adversarial attacks-particularly in black-box settings-remains a significant concern. Iterative attacks such as I-FGSM and PGD are commonly used to strengthen perturbations, but their ability to transfer across different architectures remains underexplored. In this paper, we present a systematic evaluation of adversarial transferability across both closely related architectures–Convolutional Neural Network (CNN) and Dilated CNN–and fundamentally different ones-CNN and Vision Transformer (ViT)-using both high-resolution (ANIMAL5) and low-resolution (FMNIST) datasets. To capture the impact of attack configuration, we vary the perturbation size$(\epsilon)$, step size ($\alpha$) and number of iterations. Our results show that iterative attacks tend to overfit to the source model and that their transferability decreases as the number of steps increases. This effect is further amplified when architectural differences such as dilation or attention mechanisms are present. Higher$\epsilon$values partially compensate for this drop in transferability, providing marginal improvement across settings. In addition, we show that increasing input resolution reduces transferability for CNN and Dilated CNN-based targets, whereas ViTs maintain strong transferability even from low-resolution inputs when global structure is preserved. These findings indicate that architectural generalization, rather than iterative strength alone, is a key driver of adversarial transferability.

The Sixth Workshop on Forming an Ecosystem Around Software Transformation (FEAST) revives the series, with the original five events taking place from 2016-2020. FEAST is concerned with all aspects of achieving effective, robust, and appraisable late-stage transformation of software for security. Late-stage transformations allow third parties to deeply tailor existing software to their mission, customizing it with little to no access to source code or support from the original developer.

Cyber-physical systems (CPS) are used in various safety-critical domains such as robotics, industrial manufacturing systems, and power systems. Faults and cyber attacks have been shown to cause safety violations, which can damage the system and endanger human lives. Traditional resiliency techniques fall short of protecting against cyber threats. In this article, we show how to extend resiliency to cyber resiliency for CPS using a specific combination of diversification, redundancy, and the physical inertia of the system.