Alpha Fusion Adversarial Attack Analysis Using Deep Learning

The deep learning model encompasses a powerful learning ability that integrates the feature extraction, and classification method to improve accuracy. Convolutional Neural Networks (CNN) perform well in machine learning and image processing tasks like segmentation, classification, detection, identification, etc. The CNN models are still sensitive to noise and attack. The smallest change in training images as in an adversarial attack can greatly decrease the accuracy of the CNN model. This paper presents an alpha fusion attack analysis and generates defense against adversarial attacks. The proposed work is divided into three phases: firstly, an MLSTM-based CNN classification model is developed for classifying COVID-CT images. Secondly, an alpha fusion attack is generated to fool the classification model. The alpha fusion attack is tested in the last phase on a modified LSTM-based CNN (CNN-MLSTM) model and other pre-trained models. The results of CNN models show that the accuracy of these models dropped greatly after the alpha-fusion attack. The highest F1 score before the attack was achieved is 97.45 And after the attack lowest F1 score recorded is 22%. Results elucidate the performance in terms of accuracy, precision, F1 score and Recall.     

ACTNET: End-to-End Learning of Feature Activations and Multi-stream Aggregation for Effective Instance Image Retrieval

International Journal of Computer Vision - We propose a novel CNN architecture called ACTNET for robust instance image retrieval from large-scale datasets. Our key innovation is a learnable...     

Lung nodules detection using semantic segmentation and classification with optimal features

Neural Computing and Applications - Lung cancer is a deadly disease if not diagnosed in its early stages. However, early detection of lung cancer is a challenging task due to the shape and size of...     

From dynamic influence nets to dynamic Bayesian networks: A transformation algorithm

This paper presents an algorithm to transform a dynamic influence net (DIN) into a dynamic Bayesian network (DBN). The transformation aims to bring the best of both probabilistic reasoning paradigms. The advantages of DINs lie in their ability to represent causal and time‐varying information in a compact and easy‐to‐understand manner. They facilitate a system modeler in connecting a set of desired effects and a set of actionable events through a series of dynamically changing cause and effect relationships. The resultant probabilistic model is then used to analyze different courses of action in terms of their effectiveness to achieve the desired effect(s). The major drawback of DINs is their inability to incorporate evidence that arrive during the execution of a course of action (COA). Several belief‐updating algorithms, on the other hand, have been developed for DBNs that enable a system modeler to insert evidence in dynamic probabilistic models. Dynamic Bayesian networks, however, suffer from the intractability of knowledge acquisition. The presented transformation algorithm combines the advantages of both DINs and DBNs. It enables a system analyst to capture a complex situation using a DIN and pick the best (or close‐to‐best) COA that maximizes the likelihood of achieving the desired effect. During the execution, if evidence becomes available, the DIN is converted into an equivalent DBN and beliefs of other nodes in the network are updated. If required, the selected COA can be revised on the basis of the recently received evidence. The presented methodology is applicable in domains requiring strategic level decision making in highly complex situations, such as war games, real‐time strategy video games, and business simulation games. © 2009 Wiley Periodicals, Inc.     

On the selection of software defect estimation techniques

Estimating the number of defects in a software product is an important and challenging problem. A multitude of estimation techniques have been proposed for defect prediction. However, not all techniques are applicable in all cases. The selection of the proper approach to use depends on multiple factors: the features of the approach; the availability of resources; and the goals for using the estimated defect data. In this paper a survey of existing estimation techniques and a decision support approach for selecting the most suitable defect estimation technique for a project, with specific goals, is proposed. The results of the ranking are a clear indication that no estimation technique provides a single, comprehensive solution; the selection must be done according to a given scenario. Copyright © 2009 John Wiley & Sons, Ltd.