The rapid growth of Decentraland has crafted a new frontier for digital asset investment. However, navigating and understanding this platform pose a significant challenge, especially for nonexpert users. The key obstacles include understanding market trends and price forecasting of the virtual assets, interpreting social media sentiment, and analyzing the impact of various economic factors. Furthermore, there is a lack of comprehensible, user-friendly tools to guide both the novice and experienced users in this complex, fast-evolving markets. To address this research gap, this article introducesDecentraBot, a domain specific conversational AI framework designed specifically for guiding users in making informed decisions on possible land investment and trading opportunities within Decentraland. By leveraging a systematic approach, which integrates fine-tuning methods, predictive and forecasting models, real-time data utilization, and novel prompt engineering techniques; we enable the open-domain large language models (LLMs) to transform into a domain-specific assistant capable of handling conversational, explanatory, and analytical queries effectively. To support users lacking prompting expertise, we introduce What-Next prompting; an efficient strategy that aims to minimize interaction barriers, making AI-based conversations more accessible and inclusive. Extensive experimental evaluation of DecentraBot over our proposed comprehensive fine-tune datasets demonstrates a significant performance improvement in terms of both quality and relevance of the responses to a broad spectrum of domain-specific queries. To the best of our knowledge, this is the first initiative of its kind in the realm of user-centric AI assistance within the metaverse ecosystem.

Phishing scams on the Ethereum network have become a serious threat, especially with the influx of new users into the cryptocurrency market. Current detection methods are mainly focused on long-term consistent transaction patterns with smooth temporal dynamics. However, these methods often struggle to differentiate between phishing and non-phishing users, whose behaviours may appear deceptively similar. Additionally, they face challenges such as network sparsity and data leakage, leading to significant performance limitations. To address these issues, we introduce TEMPER, a novel sequential learning framework designed to jointly capture the subtle distinctions between long- and short-term user behaviours and their correlations to provide more comprehensive insights. TEMPER effectively generates distinguishable user embeddings, enabling the accurate identification of phishing users. Unlike previous approaches, TEMPER mitigates data leakage through a novel sequential transaction sampling algorithm and addresses network sparsity with short-term temporal learning. Through extensive experimentation on three real-world Ethereum datasets, TEMPER demonstrates its efficacy by achieving a 3-4% improvement in the F1-Score compared to existing baseline models, representing a significant advancement in Ethereum phishing user detection.

Phishing scams on Ethereum have expanded with the surge of the platform, posing substantial challenges due to the sheer similarity in user behaviours and sparse temporal instances. Current methods often fail to tackle these concerns and overlook the temporal sequence of transactions, resulting in suboptimal performance. In this paper, we aim to address these gaps by focusing on the alignment of two aspects: (1) User-specific local temporal behavior, and (2) Divergences from global activity patterns of the network. Hence, we introduce CATALOG (CApturing joint TemporAl dependencies from LOcal and Global user behaviour), a novel representation learning model that jointly captures the local and global user behviours and their correlations by leveraging a dual cross-attention mechanism paired with a bi-directional Masked Language Modelling (MLM) transformer. Our proposed model simultaneously learns from local behavioral shifts, global market trends, and contextually enriched embeddings, effectively distinguishing phishing from non-phishing users while addressing existing research gaps. Extensive experiments on real-world Ethereum transaction data show that our framework improves phishing detection by 7-8% in the F1-Score along with demonstrating the generalization to Ethereum versions 1.0 and 2.0.

In recent years, the consequences of phishing scams on Ethereum have adversely affected the stability of the cryptocurrency environment. Numerous incidents have been reported that have resulted in a substantial loss of cryptocurrency. The existing literature in this area primarily leverages traditional feature engineering or network representation learning to recover crucial information from transaction records to identify suspected users. However, these methods mainly rely on handcrafted feature engineering or conventional node representation learning from a static network while ignoring the network dynamism and inherent temporal sparsity in the user behavior that results in underperformance after an extended period. This article proposes a novel sparsity-aware tensor decomposition-based architecture:SpaTeD, which retrieves efficient user representation utilizing the evolving transaction and structural information and subsequently mitigates the temporal sparsity problem. Our model is evaluated on a real-world Ethereum phishing scam dataset and reports a significant performance improvement over the baselines (96%recalland 96%F1-score). We have conducted an extensive set of experiments to verify the temporal robustness of the model. Additionally, we have provided the ablation study to demonstrate the contribution of each component of the framework.

The Ethereum blockchain platform has witnessed a surge in crypto-cybercrimes, particularly phishing attacks, resulting in significant financial losses. Analyzing the Ethereum transaction network to detect phishing users poses a set of critical challenges, including network sparsity, dynamic network fluctuations, large-scale data and significant class imbalance. Existing literature in this area primarily leverages traditional feature engineering or network representation learning to retrieve crucial information from transaction records to identify suspected users. However, these methods mainly rely on manually handcrafted features or conventional node representation learning while ignoring the inherent network sparsity and dynamic fluctuations. Hence, to alleviate these challenges, this paper introduces a novel tensor-based representation learning framework, TREAT (Temporal andRelationalAttention-basedTensor Representation Learning). TREAT models the Ethereum transaction network as a 3-dimensional tensor to preserve structural, transactional, and temporal aspects in a standalone architecture, thereby observing the rich correlation among these. The framework is coupled with a two-way self-attention mechanism alongside a rank-based tensor decomposition to comprehend the underlying evolving transaction interaction patterns while addressing the network sparsity. A Graph Neural Network layer with edge attention elevates the final representation quality, thereby yielding a 3%~4% improvement inF1-Scorewith respect to the existing baselines.

Abstract Access control of data that are outsourced to cloud storage is a challenging problem because data owners lose direct control over outsourced data. Attribute‐based encryption (ABE) is a potential cryptographic solution to provide confidentiality and flexible sharing of these outsourced data. However, the traditional ABE schemes do not meet the need of the current dynamic environment where data access not only considers the user's static and inherent attributes but also takes the user's contextual information such as location and time of access. This paper presents an improved ABE scheme using blockchain technology that can handle the frequently changing location and time attributes of data users efficiently, leading to support for fine‐grained access control of cloud storage embedding contextual information in the access policy of ABE. A prototype implementation of the proposed ABE scheme using solidity on the Ethereum platform and the experimental evaluation in terms of performance and execution cost shows a promising result.

Privacy and integrity of medical records while preserving and sharing them within any healthcare system is of high importance. Recently, India's Ayushman Bharat Digital Mission (ABDM) aims to address various issues of the existing healthcare systems and proposes a federated healthcare system to bring all the players under a common umbrella. However, it falls short on various aspects, including transparency, auditability, and traceability of activities and information within the system. In this proposal, we aim to bridge these existing gaps and propose an extension of the ABDM proposal by incorporating a blockchain layer instrumented with additional features such as traceable consent management, auditable access logs, etc., while keeping in mind its performance and scalability. We present a proof of concept of our proposal based on Hyperledger Fabric and related backend technologies and manifest experimental results to reinforce the practicality of our proposal.

In recent years, with the support of appropriate smart contract-based access control policies, blockchain technology has proven to be a compelling solution for providing a unified, trusted platform for resource sharing. However, due to the immutability property of blockchain, it can be challenging to patch or fix bugs after the deployment of a smart contract. Therefore, it is critical to ensure that the smart contract access control policies adhere to all specifications prior to their deployment, and the presence of anomalies within policies is not desirable. Thus, this paper proposes an automated policy verification and enforcement framework for Ethereum decentralized applications, which supports an automated off-chain policy verification before its deployment to the underlying blockchain. We integrate a verification engine within the off-chain module paired with a translator to convert XACML policies into Solidity smart contracts and vice-versa. Additionally, the experiments performed on benchmark XACML policies further reinforce the pragmatism of our proposal.

The recent surge of Ethereum in prominence has made it an attractive target for various kinds of crypto-crime. Phishing scams, for example, are an increasingly prevalent cybercrime in which malicious users attempt to steal funds from a user's crypto wallet. This research investigates the effects of network architectural features as well as the temporal aspects of user activities on the performance of detecting phishing users on the Ethereum transaction network. We employ traditional machine learning algorithms to evaluate our model on real-world Ethereum transaction data. The experimental results demonstrate that our proposed features identify phishing accounts efficiently and outperform the baseline models by 4% in Recall, and 5% in F1-score.

This article introduces${\sf FedRLChain}$, a novel framework for blockchain-based secure federated deep reinforcement learning, which allows users to securely and collaboratively train a Deep Reinforcement Learning (DRL) model by plugging appropriate aggregation and verification algorithms for specific problems. Unlike existing systems,${\sf FedRLChain}$adopts 1) a novel verification algorithm to prevent malicious clients, 2) an aggregation weight scheme from preventing the global model from getting biased toward any client, and 3) a variant of traditional FedAverage algorithm to accelerate the convergence process. We perform a rigorous experimental evaluation of${\sf FedRLChain}$considering the classic cart-pole problem, and we show a significant improvement in the number of epochs and time required for model convergence w.r.t. the state-of-the-art frameworks – DDQL, BAFFLE, and BASE-PIoT.

The rapid growth of Internet of Things and communication technology has provided a lot of scope for the improvement of the current healthcare services. Mobile healthcare system can be used to monitor patients’ real-time physiological information and can also help in detecting and providing emergency services to the patients. For early detection of emergency, two associated requirements are - patients’ physiological details to be received in regular intervals and the data should be processed efficiently in an automated way. Additionally, patients sensitive healthcare details need to be protected also. For his purpose, this paper proposes a blockchain-enabled emergency detection system that detects emergency conditions from patients’ encrypted physiological information without decryption and automatically triggers quick responses to provide healthcare services to the patients’ via nearby hospitals. The support of blockchain technology increases accountability, transparency, and trust concerning the storage, safeguarding, and sharing of patients’ data. We present a proof of concept of our proposal using Hyperledger Fabric, and we perform an experimental evaluation using Caliper benchmarking tool to demonstrate the performance of the system.

It is crucial to impart autonomy to robots for efficient exploration in surveillance and military applications. Most research on exploration deal largely with 2D environments using ground-based robots or 3D environments using drones. For applications requiring stealth, wall-climbing robots have an edge over drones however research is scant in 3D exploration algorithms using such robots. This paper presents a constrained 3D mapping problem and proposes a reinforcement learning-based exploration algorithm for the same using a lizard-inspired robot. The developed approach is based on a simulation-based framework in CoppeliaSim for simulating robot motion and Tensorflow for action selection algorithm using Deep Q Network (DQN). We report a number of simulation results indicating an improvement in median coverage by 20.3% using the developed DQN-based action selection over that of one generated by random action selection. Moreover, we observe that the developed DQN-based action selection approach led to more than 80% coverage within 150 steps, whereas the random action selection approach barely exceeded 60% coverage. We envisage that the developed approach can help imparting autonomy to the wall climbing stealthy robots in hostage scenarios.

The gas mechanism on the Ethereum blockchain attempts to set charges for every smart contract operation in order to prevent infinite control of computational resources by the executing transactions. To satisfy this requirement, users need to specify in their transactions how much gas fees (in terms of gas limit and gas price) they would like to pay for. In essence, these gas fees are paid to the miners in return for their computational services. Naturally, miners tend to maximize their profits by considering the transactions with higher gas fees, and as a result, the transactions with lower gas fees remain in the waiting pool for a long time. This paper proposes a machine learning-based approach to predict whether a transaction with offered gas fees is likely to be included in the blockchain within the expected time or not. Such prior prediction of transactions' waiting time definitely assists users to reset their gas fees accordingly. The proposed model is evaluated on nearly one million real transactions from Ethereum mainnet, and the experimental results demonstrate a better performance than the existing one in the literature, with an achievement of 90.18% accuracy and 0.897 F1-score when the model is trained with Random Forest on the dataset balanced with SMOTETomek.

This paper proposes a novel blockchain-based smart policing system which increases accountability, transparency, and trust concerning the storage, safeguarding, and sharing of evidence and intelligence related to ongoing investigations, criminal cases, and justice information among the stakeholders. The system allows various stakeholders, such as citizens of the country, law enforcement agencies, intelligence agencies, forensic departments, government bodies, and judges, to participate and to provide crucial services, such as filing FIR, initiating investigations, adding forensic reports, delivering justice, etc., related to smart policing. We present a proof of concept of our proposal using Hyperledger Fabric, adopting the Attribute-Based Access Control (ABAC) policy, and we perform an experimental evaluation to demonstrate the performance of the system. To the best of our knowledge, this is the first proposal on a blockchain-based smart policing system in the literature.

Dependency information (data- and/or control-dependencies) among program variables and program statements is playing crucial roles in a wide range of software-engineering activities, e.g., program slicing, information flow security analysis, debugging, code-optimization, code-reuse, code-understanding. Most existing dependency analyzers focus on mainstream languages and they do not support database applications embedding queries and data-manipulation commands. The first extension to the languages for relational database management systems, proposed by Willmor et al. in 2004, suffers from the lack of precision in the analysis primarily due to its syntax-based computation and flow insensitivity. Since then no significant contribution is found in this research direction. This paper extends the Abstract Interpretation framework for static dependency analysis of database applications, providing a semantics-based computation tunable with respect to precision. More specifically, we instantiate dependency computation by using various relational and non-relational abstract domains, yielding to a detailed comparative analysis with respect to precision and efficiency. Finally, we present a prototype$\sf{ semDDA}$, asemantics-basedDatabaseDependencyAnalyzer integrated with various abstract domains, and we present experimental evaluation results to establish the effectiveness of our approach. We show an improvement of the precision on an average of 6 percent in the interval, 11 percent in the octagon, 21 percent in the polyhedra and 7 percent in the powerset of intervals abstract domains, as compared to their syntax-based counterpart, for the chosen set of Java Server Page (JSP)-based open-source database-driven web applications as part of the GotoCode project.

The K framework is a rewrite logic-based framework for defining programming language semantics suitable for formal reasoning about programs and programming languages. In this paper, we present K-Taint, a rewriting logic-based executable semantics in the K framework for taint analysis of an imperative programming language. Our K semantics can be seen as a sound approximation of programs semantics in the corresponding security type domain. More specifically, as a foundation to this objective, we extend to the case of taint analysis the semantically sound flow-sensitive security type system by Hunt and Sands's, considering a support to the interprocedural analysis as well. With respect to the existing methods, K-Taint supports context- and flow-sensitive analysis, reduces false alarms, and provides a scalable solution. Experimental evaluation on several benchmark codes demonstrates encouraging results as an improvement in the precision of the analysis.

We introduce Tukra, a tool that allows the practical evaluation of abstract program slicing algorithms. The tool exploits the notions of statement relevancy, semantic data dependences and conditional dependences. The combination of these three notions allows Tukra to refine traditional syntax-based program dependence graphs, generating more accurate slices. We provide the architecture of the tool, some snapshots describing how it works, and some preliminary experimental results giving evidence of the accuracy improvements it supports.

In this paper, we propose an obfuscation/ deobfuscation based technique to detect the presence of possible SQL Injection Attacks (SQLIA) in a query before submitting it to a DBMS. This technique combines static and dynamic analysis. In the static phase, the queries in the application are replaced by queries in obfuscated form. The main idea behind obfuscation is to isolate all the atomic formulas from other control elements of the query. During the dynamic phase, the user inputs are merged into the obfuscated atomic formulas, and the dynamic verifier analysis the presence of possible SQLIA at atomic formula level. Finally, a deobfuscation step is performed to recover the original query before submitting it to the DBMS.