Abstract

Recent years have witnessed a massive growth in the proliferation of fake news online. User-generated content is a blend of text and visual information leading to producing different variants of fake news. As a result, researchers started targeting multimodal methods for fake news detection. Existing methods capture high-level information from different modalities and jointly model them to decide. Given multiple input modalities, we hypothesize that not all modalities may be equally responsible for decision-making. Hence, this paper presents a novel architecture that effectively identifies and suppresses information from weaker modalities and extracts relevant information from the strong modality on a per-sample basis. We also establish intra-modality relationship by extracting fine-grained image and text features. We conduct extensive experiments on real-world datasets to show that our approach outperforms the state-of-the-art by an average of 3.05% and 4.525% on accuracy and F1-score, respectively. We also release the code, implementation details, and model checkpoints for the community’s interest.1

Abstract

NFT or Non-Fungible Token is a token that certifies a digital asset to be unique. A wide range of assets including, digital art, music, tweets, memes, are being sold as NFTs. NFT-related content has been widely shared on social media sites such as Twitter. We aim to understand the dominant factors that influence NFT asset valuation. Towards this objective, we create a first-of-its-kind dataset linking Twitter and OpenSea (the largest NFT marketplace) to capture social media profiles and linked NFT assets. Our dataset contains 245,159 tweets posted by 17,155 unique users, directly linking 62,997 NFT assets on OpenSea worth 19 Million USD. We have made the dataset public. We analyze the growth of NFTs, characterize the Twitter users promoting NFT assets, and gauge the impact of Twitter features on the virality of an NFT. Further, we investigate the effectiveness of different social media and NFT platform features by experimenting with multiple machine learning and deep learning models to predict an asset's value. Our results show that social media features improve the accuracy by 6% over baseline models that use only NFT platform features. Among social media features, count of user membership lists, number of likes and retweets are important features.

Abstract

Deepfakes are synthetic content generated using advanced deep learning and AI technologies. The advancement of technology has created opportunities for anyone to create and share deepfakes

Abstract

This article proposes a new blockchain-envisioned key management protocol for artificial intelligence (AI)-enabled industrial cyber–physical systems (ICPSs). The designed key management protocol enables key establishment among the Internet of Things (IoT)-enabled smart devices and their respective gateway nodes. The blocks partially constructed with secure data from smart devices by fog servers are provided to cloud servers that are responsible for completing blocks, and then mining those blocks for verification and addition in the blockchain. The most important application of the private blockchain construction is to apply AI algorithms for accurate predictions in Big data analytics. A detailed security analysis along with formal security verification show that the proposed scheme resists various potential attacks in an ICPS environment. Moreover, practical testbed experiments have been conducted using the multiprecision integer and rational arithmetic cryptographic library (MIRACL). Furthermore, a detailed comparative analysis shows superiority of the proposed scheme over recent relevant schemes. In addition, the practical implementation using the blockchain for the proposed scheme demonstrates the total computational costs when the number of transactions per block and also the number of blocks mined in the blockchain are varied.

Abstract

In this article, we present an efficient algorithm for solving a class of chance-constrained optimization under nonparametric uncertainty. Our algorithm is built on the possibility of representing arbitrary distributions as functions in Reproducing Kernel Hilbert Space (RKHS). We use this foundation to formulate chance-constrained optimization as one of minimizing the distance between a desired distribution and the distribution of the constraint functions in the RKHS. We provide a systematic way of constructing the desired distribution based on the notion of scenario approximation. Furthermore, we use the kernel trick to show that the computational complexity of our reformulated optimization problem is comparable to solving a deterministic variant of the chance-constrained optimization. We validate our formulation on two important robotic applications: 1) reactive collision avoidance of mobile robots in uncertain dynamic environments and 2) inverse-dynamics-based path-tracking of manipulators under perception uncertainty. In both these applications, the underlying chance constraints are defined over nonlinear and nonconvex functions of uncertain parameters and possibly also decision variables. We also benchmark our formulation with the existing approaches in terms of sample complexity and the achieved optimal cost highlighting significant improvements in

Abstract

A deep learning-based approach called Deep-StRIP is proposed for the detection of two major class of structural repeats, namely, Class III and Class IV repeats in Kajava's classification, which covers over 90% of known structural repeats

Abstract

Advances in mobile computing have paved the way for new types of distributed applications that can be executed solely by mobile devices on Device-to-Device (D2D) ecosystems (e.g., crowdsensing). Sophisticated applications, like cryptocurrencies, need distributed ledgers (DLs) to function. DLs, such as blockchains and directed acyclic graphs (DAGs), employ consensus protocols to add data in the form of blocks. However, such protocols are designed for resourceful devices that are interconnected via the Internet. Moreover, existing DLs are not deployable to D2D ecosystems since their storage needs are continuously increasing. In this work, we introduce and analyze Mneme, a DAG-based DL that can be maintained solely by mobile devices. Mneme utilizes two novel consensus protocols: 1) Proof of Context (PoC) and 2) Proof of Equivalence (PoE). PoC employs users’ context to add data on Mneme. PoE is executed periodically to summarize data and produce equivalent blocks that require less storage. We analyze Mneme’s security and justify the ability of PoC and PoE to guarantee the characteristics of DLs: persistence and liveness. Furthermore, we analyze potential attacks from malicious users and prove that the probability of a successful attack is inversely

Abstract

Phase change materials are attractive as well as being selected as one of the incredibly fascinating materials relating to the high-energy storage system. Phase change materials (PCM) can absorb as well as release thermal energy throughout the melting and freezing process. In recent times, the phase change materials are the feasible option for lowering down the energy consumption and for enhancing the thermal comfort in houses. In this paper, a comprehensive summary of the phase-change materials (PCM) in state of the art is presented. Primary objective of this review is to overview most of the open scientific studies on regarding fatty acid, and carbon allotropes based fatty acid, fatty alcohol phase change materials. Also, this paper is based on earlier scientific studies to consider the variety of references that have been discussed by the authors as well as viewed as the leading contribution.

Abstract

An effective earthquake (Mw 7.9) struck Alaska on 3 November, 2002. It ruptured 340 km along three faults namely, the Susitna Glacier, Denali and Totschunda faults in central Alaska. The earthquake was recorded at 23 stations in Alaska and the Peak Ground Acceleration (PGA) of 0.32g was recorded at station PS10, which was located 3 km from the fault rupture. In this study, strike-slip Denali fault has been considered for studying the characteristics of ground motions through modified semiempirical approach. The ground motion records of the 2002 Denali earthquake are generated through MATLAB code. The results revealed that modified semi-empirical approach is fairly good in agreement with observed ground motion records at all stations. A perfect match is observed between Fourier amplitude spectra of simulated and observed ground motions at PS09 and CARLO stations. A good match is observed between elastic response spectra of observed and simulated ground motions. Keywords: Denali Earthquake, Fourier Amplitude Spectrum, Ground Motion Prediction Equation, Synthetic Accelerogram.

Abstract

Targeted image retrieval has long been a challenging problem since each person has a different perception of different features leading to inconsistency among users in describing the details of a particular image. Due to this, each user needs a system personalized according to the way they have structured the image in their mind. One important application of this task is suspect identifcation in forensic investigations where a witness needs to identify the suspect from an existing criminal database. Existing methods require the attributes for each image or suffer from poor latency during training and inference. We propose a new approach to tackle this problem through explicit relevance feedback by introducing a novel loss function and a corresponding scoring function. For this, we leverage contrastive learning on the user feedback to generate the next set of suggested images while improving the level of personalization with each user feedback iteration.