Manually backporting critical patches to long-term support versions is both error-prone and often overlooked, resulting in substantial security risks. Progress in this area is constrained by the absence of datasets that capture the semantic complexities across versions, inherent to backporting in large Java ecosystems. To address this gap, we present JavaBackports, a curated dataset of 491 real-world backport instances, systematically selected and manually validated from more than 11,000 candidate patches in fifteen widely used open-source Java projects: Druid, Elasticsearch, Hadoop, Kafka, among others and four major JDK versions (jdk11, jdk17, jdk21, jdk25). To assess the utility of JavaBackports, we conduct preliminary experiments to evaluate the effectiveness of the state-of-the-art Large Language Models (LLMs) in zero-shot automatic patch backporting. The results indicate that current LLMs struggle with backporting tasks, particularly when the required changes involve non-trivial logical or structural modifications. These findings demonstrate both the difficulty of the problem and the potential of JavaBackports to stimulate new research directions in automated software maintenance and repair.

Human Activity Recognition (HAR) is essential in various fields, including healthcare, surveillance, and sports. HAR based on Inertial Measurement Unit (IMU) sensor data has recently gained attention due to its non-intrusive and more straightforward data acquisition process compared to video-based or electromyogram sensor-based approaches. Human activities exhibit complex spatiotemporal dynamics, necessitating the extraction of discriminative spatiotemporal features from IMU data to develop effective HAR systems. While deep learning models have been extensively explored for HAR, existing approaches often struggle to capture these intricate patterns. Further, they overlook the coordinated movements across multiple body parts during activities and utilizing the relationship among sensors positioned on different body parts to improve HAR accuracy. This paper presents a novel HAR framework called STDual-X, which employs Spatio-Temporal Dual Attention Transformers (STDAT) with Cross-Sensor Attention(CSA) to improve HAR accuracy. STDAT extracts discriminative spatiotemporal patterns from IMU sensor data for HAR, and CSA enriches the features by incorporating sensor relationships. Experimental results using public datasets demonstrate the effectiveness of the proposed model, achieving state-of-the-art accuracies of 97.02% on PAMAP2, 95.43% on Opportunity, and 98.80% on UCI-HAR.

This article presents the Keystroke Verification Challenge - onGoing (KVC-onGoing) 1 1 https://sites.google.com/view/bida-kvc/ . , on which researchers can easily benchmark their systems in a common platform using large-scale public databases, the Aalto University Keystroke databases, and a standard experimental protocol. The keystroke data consist of tweet-long sequences of variable transcript text from over 185,000 subjects, acquired through desktop and mobile keyboards simulating real-life conditions. The results on the evaluation set of KVC-onGoing have proved the high discriminative power of keystroke dynamics, reaching values as low as 3.33% of Equal Error Rate (EER) and 11.96% of False Non-Match Rate (FNMR) @1% False Match Rate (FMR) in the desktop scenario, and 3.61% of EER and 17.44% of FNMR @1% at FMR in the mobile scenario, significantly improving previous state-of-the-art results. Concerning demographic fairness, the analyzed scores reflect the subjects’ age and gender to various extents, not negligible in a few cases. The framework runs on CodaLab 2 2 https://codalab.lisn.upsaclay.fr/competitions/14063 . . • We set up a novel framework for developing and evaluating keystroke biometrics. • We designed a unified experimental protocol with desktop and mobile scenarios. • We employ the biggest databases of keystroke dynamics, with over 185,000 subjects. • We provide a competitive performance baseline based on a limited-time challenge. • We provide a first exploration of the biometric fairness of keystroke dynamics.

Automated Program Repair (APR) improves developer productivity by saving debugging and bug-fixing time. While APR has been extensively explored for C/C++ and Java programs, there is little research on bugs in PHP programs due to the lack of a benchmark PHP bug dataset. This is surprising given that PHP has been one of the most widely used server-side languages for over two decades, being used in a variety of contexts such as e-commerce, social networking, and content management. This paper presents a benchmark dataset of PHP bugs on real-world applications called BugsPHP, which can enable research on analysis, testing, and repair for PHP programs. The dataset consists of training and test datasets, separately curated from GitHub and processed locally. The training dataset includes more than 600,000 bug-fixing commits. The test dataset contains 513 manually validated bug-fixing commits equipped with developer-provided test cases to assess patch correctness.

Institute, Warsaw, Poland This paper describes the results of the IEEE BigData 2023 Keystroke Verification Challenge1(KVC), that considers the biometric verification performance of Keystroke Dynamics (KD), captured as tweet-long sequences of variable transcript text from over 185,000 subjects. The data are obtained from two of the largest public databases of KD up to date, the Aalto Desktop and Mobile Keystroke Databases, guaranteeing a minimum amount of data per subject, age and gender annotations, absence of corrupted data, and avoiding excessively unbalanced subject distributions with respect to the considered demographic attributes. Several neural architectures were proposed by the participants, leading to global Equal Error Rates (EERs) as low as 3.33% and 3.61% achieved by the best team respectively in the desktop and mobile scenario, outperforming the current state of the art biometric verification performance for KD. Hosted on CodaLab2, the KVC will be made ongoing to represent a useful tool for the research community to compare different approaches under the same experimental conditions and to deepen the knowledge of the field.

Continuous Authentication (CA) using behavioural biometrics is a type of biometric identification that recognizes individuals based on their unique behavioural characteristics, like their typing style. However, the existing systems using keystroke or touch stroke data have limited accuracy and reliability. To improve this, smartphones’ Inertial Measurement Unit (IMU) sensors, which include accelerometers, gyroscopes, and magnetometers, can gather data on users’ behavioural patterns, such as how they hold their phones. Combining this IMU data with keystroke data can enhance the accuracy of behavioural biometrics-based CA. This paper proposes BehaveFormer, a new framework that employs keystroke and IMU data to create a reliable and accurate behavioural biometric CA system. It includes two Spatio-Temporal Dual Attention Transformers (STDAT), a novel transformer we introduce to extract more discriminative features from keystroke dynamics. Experimental results on three publicly available datasets (Aalto DB, HMOG DB, and HuMIdb) demonstrate that BehaveFormer outperforms the state-of-the-art behavioural biometric-based CA systems. For instance, BehaveFormer achieved an EER of 2.95% on the HuMIdb. Additionally, the proposed STDAT has been shown to improve the BehaveFormer system even when only keystroke data is used. For example, BehaveFormer achieved an EER of 1.80%. The code is available at https://github.com/DilshanSenarath/BehaveFormer.

Learning concepts that are consistent with human perception is important for Deep Neural Networks to win end-user trust. Post-hoc interpretation methods lack transparency in the feature representations learned by the models. This work proposes a guided learning approach with an additional concept layer in a CNN-based architecture to learn the associations between visual features and word phrases. We design an objective function that optimizes both prediction accuracy and semantics of the learned feature representations. Experiment results demonstrate that the proposed model can learn concepts that are consistent with human perception and their corresponding contributions to the model decision without compromising accuracy. Further, these learned concepts are transferable to new classes of objects that have similar concepts.

Existing works have generated explanations for deep neural network decisions to provide insights into model behavior. We observe that these explanations can also be used to identify concepts that caused misclassifications. This allows us to understand the possible limitations of the dataset used to train the model, particularly the under-represented regions in the dataset. This work proposes a framework that utilizes concept-based explanations to automatically augment the dataset with new images that can cover these under-represented regions to improve the model performance. The framework is able to use the explanations generated by both interpretable classifiers and post-hoc explanations from black-box classifiers. Experiment results demonstrate that the proposed approach improves the accuracy of classifiers compared to state-of-the-art augmentation strategies.

Explaining the decisions of a Deep Learning Network is imperative to safeguard end-user trust. Such explanations must be intuitive, descriptive, and faithfully explain why a model makes its decisions. In this work, we propose a framework called FLEX (Faithful Linguistic EXplanations) that generates post-hoc linguistic justifications to rationalize the decision of a Convolutional Neural Network. FLEX explains a model’s decision in terms of features that are responsible for the decision. We derive a novel way to associate such features to words, and introduce a new decision-relevance metric that measures the faithfulness of an explanation to a model’s reasoning. Experiment results on two benchmark datasets demonstrate that the proposed framework can generate discriminative and faithful explanations compared to state-of-the-art explanation generators. We also show how FLEX can generate explanations for images of unseen classes as well as automatically annotate objects in images.