Information stored via blockchain’s incremental method enforces data immutability on distributed computer storage. However, storing data incrementally in blocks introduces a temporal constraint, namely, a linear time cost to search for historical blockchain data. Indexing computer data is a well-known technique to quicken retrieval times, with successful blockchain-specific techniques being derived from the skip list data structure, because redundant and obsolete index fragments are not stored. However, upon evaluation of these append-only deterministic skip list indexes, it is evident that a most recent version bias is introduced. Once again, it impairs the retrieval of historical blockchain data. To address this problem, we introduce the Ternary Tree Enhanced Append-only Skip List (TEASL) index. This composite index exploits the known inverse relationship between a binary tree and a deterministic skip list and extends this relationship to utilise a ternary tree. Empirical analysis and comparison of existing indexing techniques demonstrates enhanced search query traversal performance, regardless of where the data is located in the blockchain. Furthermore, TEASL does not introduce any additional storage cost. The TEASL indexing technique is proven to be the fastest append-only skip list-based indexing technique for blockchain. The code supporting this indexing technique is publicly available on GitHub https://github.com/jarednewell/TEASL/ . • TEASL’s transformational algorithm constructs a ternary tree search index from an append-only skip list, elaborating on the known inverse relationship between a binary tree and a deterministic skip list and applies it to a ternary search tree. • The ternary tree is constructed from the append-only skip list data structure sequentially and in real-time with blockchain block updates. Moreover, no index data duplication exists. That is, all previously constructed updates are required to form a complete index. • The TEASL index has superior search traversal performance which is 85.71 % faster than the current fastest append-only skip list indexing technique for blockchain and is equally as storage-efficient. TEASL has more constant blockchain data retrieval times while adapting by remaining optimal and current as the blockchain increases in size. • TEASL is suitable for a distributed client-server model which is blockchain. In this distributed configuration, index traversal occurs in two steps: First, the local ternary tree in the TEASL index is accessed on the client device, thus reducing the search space size. Second, data is retrieved from the blockchain server via the EASL index, refined by the results of the ternary tree. This reduces the cost of data retrieval via the network. • The TEASL construction algorithm allows the granularity of the ternary tree to be increased or reduced, allowing a trade-off between TEASL’s query performance times and the storage performance. This allows for the adaptation to different resource-constrained client devices, such as IoT hardware types.

Protecting software supply chains from malicious packages is paramount in the evolving landscape of software development. Attacks on the software supply chain involve attackers injecting harmful software into commonly used packages or libraries in a software repository. For instance, JavaScript uses Node Package Manager (NPM), and Python uses Python Package Index (PyPi) as their respective package repositories. In the past, NPM has had vulnerabilities such as the event-stream incident, where a malicious package was introduced into a popular NPM package, potentially impacting a wide range of projects. As the integration of third-party packages becomes increasingly ubiquitous in modern software development, accelerating the creation and deployment of applications, the need for a robust detection mechanism has become critical. On the other hand, due to the sheer volume of new packages being released daily, the task of identifying malicious packages presents a significant challenge. To address this issue, in this paper, we introduce a metadata-based malicious package detection model, MeMPtec. This model extracts a set of features from package metadata information. These extracted features are classified as either easy-to-manipulate (ETM) or difficult-to-manipulate (DTM) features based on monotonicity and restricted control properties. By utilising these metadata features, not only do we improve the effectiveness of detecting malicious packages, but also we demonstrate its resistance to adversarial attacks in comparison with existing state-of-the-art. Our experiments indicate a significant reduction in both false positives (up to 97.56%) and false negatives (up to 91.86%).

Class imbalance treatment methods and cost-sensitive classification algorithms are typically treated as two independent research areas. However, many of these techniques have properties in common. After providing a background to the two fields of research, this article identifies the fundamental mechanism which is common to both. Using this mechanism, a taxonomy is created which encompasses approaches to both class imbalance treatment and cost-sensitive classification. Through this survey, we aim to bridge the gap between the two fields such that lessons from one field may be applied to the other. Many data mining tasks are naturally both class imbalanced and cost-sensitive. This survey is useful for researchers and practitioners approaching these tasks as it provides a detailed overview of approaches in both fields. Many of the surveyed techniques are classifier independent. However, we chose to focus on techniques which were either decision tree-based or compatible with decision trees. This choice was based on the popularity and novelty of their application to both fields.

Text documents are often mapped to vectors of binary values where 1 indicates the presence of a word and 0 indicates the absence. The vectors are then used to train predictive models. In tree-based ensemble models, predictions from some decision trees may be made purely from absent words. This type of predictions should be trusted less as absent words can be interpreted in multiple ways. In this work, we propose to improve the comprehensibility and accuracy of ensemble models by distinguishing word presence and absence. The presented method weights predictions based on word presence. Experimental results on 35 real text datasets indicate that our method outperforms state-of-the-art ensemble methods on various text classification tasks.

The Random Forest (RF) classifiers are suitable for dealing with the high dimensional noisy data in text classification. An RF model comprises a set of decision trees each of which is trained using random subsets of features. Given an instance, the prediction by the RF is obtained via majority voting of the predictions of all the trees in the forest. However, different test instances would have different values for the features used in the trees and the trees should contribute differently to the predictions. This diverse contribution of the trees is not considered in traditional RFs. Many approaches have been proposed to model the diverse contributions by selecting a subset of trees for each instance. This paper is among these approaches. It proposes a Semantics Aware Random Forest (SARF) classifier. SARF extracts the features used by trees to generate the predictions and selects a subset of the predictions for which the features are relevant to the predicted classes. We evaluated SARF's classification performance on $30$ real-world text datasets and assessed its competitiveness with state-of-the-art ensemble selection methods. The results demonstrate the superior performance of the proposed approach in textual information retrieval and initiate a new direction of research to utilise interpretability of classifiers.

Millions of users place data about themselves on on-line social networks and, while probably they have an interest on some of this information to be publicly available, they certainly may consider some of this information shall remain confidential. Simultaneously, the data provides benefits as such data enables personalization which increases the quality of service; and thus, it is regularly analyzed with data mining techniques. Since privacy directly correlates to the control users have regarding the data about themselves, this paper provides a technique by which operators of on-line social networks can improve the service to their users by empowering the users to appraise the privacy risks that some information they provide results in others inferring confidential attributes.