17 July 2023 in ACM Computing Surveys
In the past few years, it has become increasingly evident that deep neural networks are not resilient enough to withstand adversarial perturbations in input data, leaving them vulnerable to attack. Various authors have proposed strong adversarial attacks for computer vision and Natural Language Processing (NLP) tasks. As a response, many defense mechanisms have also been proposed to prevent these networks from failing. The significance of defending neural networks against adversarial attacks lies in ensuring that the model’s predictions remain unchanged even if the input data is perturbed. Several methods for adversarial defense in NLP have been proposed, catering to different NLP tasks such as text classification, named entity recognition, and natural language inference. Some of these methods not only defend neural networks against adversarial attacks but also act as a regularization mechanism during training, saving the model from overfitting. This survey aims to review the various methods proposed for adversarial defenses in NLP over the past few years by introducing a novel taxonomy. The survey also highlights the fragility of advanced deep neural networks in NLP and the challenges involved in defending them.
10 December 2023 in Automation in Construction
25 February 2022 in Multimedia Tools and Applications
Indoor scene reconstruction and generating a 2D/3D floor plan is a widely explored problem. In the recent years a few algorithms have been proposed, which either use RGB-D images, requiring a depth capturing camera or depend upon panoramic images, assuming little to no occlusion in the room. In this work, we propose a framework named GRIHA (Generating Room Interior of a House using ARcore), which takes advantage of RGB images taken from a conventional mobile phone camera. The proposed work uses Simultaneous Localization And Mapping (SLAM) technology to estimate the 3D transformations required for layout generation. GRIHA uses SLAM based Google ARcore library for camera pose estimation while capturing the images. It gives the user freedom to generate a layout by merely taking a few conventional photos, rather than relying on specialized depth hardware or occlusion-free panoramic images. We have compared GRIHA with other existing methods and obtained superior results. Moreover, the system is tested on multiple hardware platforms to test the dependency and efficiency.