Weber Law Based Approach for Multi-Class Image Forgery Detection

Today’s forensic science introduces a new research area for digital image analysis formultimedia security.So,Image authentication issues have been raised due to the wide use of image manipulation software to obtain an illegitimate benefit or createmisleading publicity by using tempered images.Exiting forgery detectionmethods can classify only one of the most widely used Copy-Move and splicing forgeries.However,an image can contain one or more types of forgeries.This study has proposed a hybridmethod for classifying Copy-Move and splicing images using texture information of images in the spatial domain.Firstly,images are divided into equal blocks to get scale-invariant features.Weber law has been used for getting texture features,and finally,XGBOOST is used to classify both Copy-Move and splicing forgery.The proposed method classified three types of forgeries,i.e.,splicing,Copy-Move,and healthy.Benchmarked(CASIA 2.0,MICCF200)and RCMFD datasets are used for training and testing.On average,the proposed method achieved 97.3% accuracy on benchmarked datasets and 98.3% on RCMFD datasets by applying 10-fold cross-validation,which is far better than existing methods.

A Recurrent Neural Network for Multimodal Anomaly Detection by Using Spatio-Temporal Audio-Visual Data

In video surveillance,anomaly detection requires training machine learning models on spatio-temporal video sequences.However,sometimes the video-only data is not sufficient to accurately detect all the abnormal activities.Therefore,we propose a novel audio-visual spatiotemporal autoencoder specifically designed to detect anomalies for video surveillance by utilizing audio data along with video data.This paper presents a competitive approach to a multi-modal recurrent neural network for anomaly detection that combines separate spatial and temporal autoencoders to leverage both spatial and temporal features in audio-visual data.The proposed model is trained to produce low reconstruction error for normal data and high error for abnormal data,effectively distinguishing between the two and assigning an anomaly score.Training is conducted on normal datasets,while testing is performed on both normal and anomalous datasets.The anomaly scores from the models are combined using a late fusion technique,and a deep dense layer model is trained to produce decisive scores indicating whether a sequence is normal or anomalous.The model’s performance is evaluated on the University of California,San Diego Pedestrian 2(UCSD PED 2),University of Minnesota(UMN),and Tampere University of Technology(TUT)Rare Sound Events datasets using six evaluation metrics.It is compared with state-of-the-art methods depicting a high Area Under Curve(AUC)and a low Equal Error Rate(EER),achieving an(AUC)of 93.1 and an(EER)of 8.1 for the(UCSD)dataset,and an(AUC)of 94.9 and an(EER)of 5.9 for the UMN dataset.The evaluations demonstrate that the joint results from the combined audio-visual model outperform those from separate models,highlighting the competitive advantage of the proposed multi-modal approach.

Privacy and security federated reference architecture for Internet of Things

Physical objects are getting connected to the Internet at an exceptional rate,making the idea of the Internet of Things(IoT)a reality.The IoT ecosystem is evident everywhere in the form of smart homes,health care systems,wearables,connected vehicles,and industries.This has given rise to risks associated with the privacy and security of systems.Security issues and cyber attacks on IoT devices may potentially hinder the growth of IoT products due to deficiencies in the architecture.To counter these issues,we need to implement privacy and security right from the building blocks of IoT.The IoT architecture has evolved over the years,improving the stack of architecture with new solutions such as scalability,management,interoperability,and extensibility.This emphasizes the need to standardize and organize the IoT reference architecture in federation with privacy and security concerns.In this study,we examine and analyze 12 existing IoT reference architectures to identify their shortcomings on the basis of the requirements addressed in the standards.We propose an architecture,the privacy-federated IoT security reference architecture(PF-IoT-SRA),which interprets all the involved privacy metrics and counters major threats and attacks in the IoT communication environment.It is a step toward the standardization of the domain architecture.We effectively validate our proposed reference architecture using the architecture trade-off analysis method(ATAM),an industry-recognized scenario-based approach.