This paper presents an extended version of Deeper, a search-based simulation-integrated test solution that generates failure-revealing test scenarios for testing a deep neural network-based lane-keeping system. In the newly proposed version, we utilize a new set of bio-inspired search algorithms, genetic algorithm (GA), $({\mu}+{\lambda})$ and $({\mu},{\lambda})$ evolution strategies (ES), and particle swarm optimization (PSO), that leverage a quality population seed and domain-specific cross-over and mutation operations tailored for the presentation model used for modeling the test scenarios. In order to demonstrate the capabilities of the new test generators within Deeper, we carry out an empirical evaluation and comparison with regard to the results of five participating tools in the cyber-physical systems testing competition at SBST 2021. Our evaluation shows the newly proposed test generators in Deeper not only represent a considerable improvement on the previous version but also prove to be effective and efficient in provoking a considerable number of diverse failure-revealing test scenarios for testing an ML-driven lane-keeping system. They can trigger several failures while promoting test scenario diversity, under a limited test time budget, high target failure severity, and strict speed limit constraints.
相關內容
With the implementation of the new EU regulation 2022/1426 regarding the type-approval of the automated driving system (ADS) of fully automated vehicles, scenario-based testing has gained significant importance in evaluating the performance and safety of advanced driver assistance systems and automated driving systems. However, the exploration and generation of concrete scenarios from a single logical scenario can often lead to a number of similar or redundant scenarios, which may not contribute to the testing goals. This paper focuses on the the goal to reduce the scenario set by clustering concrete scenarios from a single logical scenario. By employing clustering techniques, redundant and uninteresting scenarios can be identified and eliminated, resulting in a representative scenario set. This reduction allows for a more focused and efficient testing process, enabling the allocation of resources to the most relevant and critical scenarios. Furthermore, the identified clusters can provide valuable insights into the scenario space, revealing patterns and potential problems with the system's behavior.
The challenges expected for the next era of the Large Hadron Collider (LHC), both in terms of storage and computing resources, provide LHC experiments with a strong motivation for evaluating ways of rethinking their computing models at many levels. Great efforts have been put into optimizing the computing resource utilization for the data analysis, which leads both to lower hardware requirements and faster turnaround for physics analyses. In this scenario, the Compact Muon Solenoid (CMS) collaboration is involved in several activities aimed at benchmarking different solutions for running High Energy Physics (HEP) analysis workflows. A promising solution is evolving software towards more user-friendly approaches featuring a declarative programming model and interactive workflows. The computing infrastructure should keep up with this trend by offering on the one side modern interfaces, and on the other side hiding the complexity of the underlying environment, while efficiently leveraging the already deployed grid infrastructure and scaling toward opportunistic resources like public cloud or HPC centers. This article presents the first example of using the ROOT RDataFrame technology to exploit such next-generation approaches for a production-grade CMS physics analysis. A new analysis facility is created to offer users a modern interactive web interface based on JupyterLab that can leverage HTCondor-based grid resources on different geographical sites. The physics analysis is converted from a legacy iterative approach to the modern declarative approach offered by RDataFrame and distributed over multiple computing nodes. The new scenario offers not only an overall improved programming experience, but also an order of magnitude speedup increase with respect to the previous approach.
Software Engineering is an applied discipline and concepts are difficult to grasp only at a theoretical level alone. In the context of a project management course, we introduced and evaluated the use of software process simulation (SPS) based games for improving students' understanding of software development processes. The effects of the intervention were measured by evaluating the students' arguments for choosing a particular development process. The arguments were assessed with the Evidence-Based Reasoning framework, which was extended to assess the strength of an argument. The results indicate that students generally have difficulty providing strong arguments for their choice of process models. Nevertheless, the assessment indicates that the intervention of the SPS game had a positive impact on the students' arguments. Even though the illustrated argument assessment approach can be used to provide formative feedback to students, its use is rather costly and cannot be considered a replacement for traditional assessments.
The potential of artificial intelligence (AI)-based large language models (LLMs) holds considerable promise in revolutionizing education, research, and practice. However, distinguishing between human-written and AI-generated text has become a significant task. This paper presents a comparative study, introducing a novel dataset of human-written and LLM-generated texts in different genres: essays, stories, poetry, and Python code. We employ several machine learning models to classify the texts. Results demonstrate the efficacy of these models in discerning between human and AI-generated text, despite the dataset's limited sample size. However, the task becomes more challenging when classifying GPT-generated text, particularly in story writing. The results indicate that the models exhibit superior performance in binary classification tasks, such as distinguishing human-generated text from a specific LLM, compared to the more complex multiclass tasks that involve discerning among human-generated and multiple LLMs. Our findings provide insightful implications for AI text detection while our dataset paves the way for future research in this evolving area.
We present Project Florida, a system architecture and software development kit (SDK) enabling deployment of large-scale Federated Learning (FL) solutions across a heterogeneous device ecosystem. Federated learning is an approach to machine learning based on a strong data sovereignty principle, i.e., that privacy and security of data is best enabled by storing it at its origin, whether on end-user devices or in segregated cloud storage silos. Federated learning enables model training across devices and silos while the training data remains within its security boundary, by distributing a model snapshot to a client running inside the boundary, running client code to update the model, and then aggregating updated snapshots across many clients in a central orchestrator. Deploying a FL solution requires implementation of complex privacy and security mechanisms as well as scalable orchestration infrastructure. Scale and performance is a paramount concern, as the model training process benefits from full participation of many client devices, which may have a wide variety of performance characteristics. Project Florida aims to simplify the task of deploying cross-device FL solutions by providing cloud-hosted infrastructure and accompanying task management interfaces, as well as a multi-platform SDK supporting most major programming languages including C++, Java, and Python, enabling FL training across a wide range of operating system (OS) and hardware specifications. The architecture decouples service management from the FL workflow, enabling a cloud service provider to deliver FL-as-a-service (FLaaS) to ML engineers and application developers. We present an overview of Florida, including a description of the architecture, sample code, and illustrative experiments demonstrating system capabilities.
This paper explores the innovative use of simulation environments to enhance data acquisition and diagnostics in veterinary medicine, focusing specifically on gait analysis in dogs. The study harnesses the power of Blender and the Blenderproc library to generate synthetic datasets that reflect diverse anatomical, environmental, and behavioral conditions. The generated data, represented in graph form and standardized for optimal analysis, is utilized to train machine learning algorithms for identifying normal and abnormal gaits. Two distinct datasets with varying degrees of camera angle granularity are created to further investigate the influence of camera perspective on model accuracy. Preliminary results suggest that this simulation-based approach holds promise for advancing veterinary diagnostics by enabling more precise data acquisition and more effective machine learning models. By integrating synthetic and real-world patient data, the study lays a robust foundation for improving overall effectiveness and efficiency in veterinary medicine.
Wildlife camera trap images are being used extensively to investigate animal abundance, habitat associations, and behavior, which is complicated by the fact that experts must first classify the images manually. Artificial intelligence systems can take over this task but usually need a large number of already-labeled training images to achieve sufficient performance. This requirement necessitates human expert labor and poses a particular challenge for projects with few cameras or short durations. We propose a label-efficient learning strategy that enables researchers with small or medium-sized image databases to leverage the potential of modern machine learning, thus freeing crucial resources for subsequent analyses. Our methodological proposal is two-fold: (1) We improve current strategies of combining object detection and image classification by tuning the hyperparameters of both models. (2) We provide an active learning (AL) system that allows training deep learning models very efficiently in terms of required human-labeled training images. We supply a software package that enables researchers to use these methods directly and thereby ensure the broad applicability of the proposed framework in ecological practice. We show that our tuning strategy improves predictive performance. We demonstrate how the AL pipeline reduces the amount of pre-labeled data needed to achieve a specific predictive performance and that it is especially valuable for improving out-of-sample predictive performance. We conclude that the combination of tuning and AL increases predictive performance substantially. Furthermore, we argue that our work can broadly impact the community through the ready-to-use software package provided. Finally, the publication of our models tailored to European wildlife data enriches existing model bases mostly trained on data from Africa and North America.
Due to the widespread application of deep neural networks~(DNNs) in safety-critical tasks, deep learning testing has drawn increasing attention. During the testing process, test cases that have been fuzzed or selected using test metrics are fed into the model to find fault-inducing test units (e.g., neurons and feature maps, activating which will almost certainly result in a model error) and report them to the DNN developer, who subsequently repair them~(e.g., retraining the model with test cases). Current test metrics, however, are primarily concerned with the neurons, which means that test cases that are discovered either by guided fuzzing or selection with these metrics focus on detecting fault-inducing neurons while failing to detect fault-inducing feature maps. In this work, we propose DeepFeature, which tests DNNs from the feature map level. When testing is conducted, DeepFeature will scrutinize every internal feature map in the model and identify vulnerabilities that can be enhanced through repairing to increase the model's overall performance. Exhaustive experiments are conducted to demonstrate that (1) DeepFeature is a strong tool for detecting the model's vulnerable feature maps; (2) DeepFeature's test case selection has a high fault detection rate and can detect more types of faults~(comparing DeepFeature to coverage-guided selection techniques, the fault detection rate is increased by 49.32\%). (3) DeepFeature's fuzzer also outperforms current fuzzing techniques and generates valuable test cases more efficiently.
The fairness of machine learning (ML) approaches is critical to the reliability of modern artificial intelligence systems. Despite extensive study on this topic, the fairness of ML models in the software engineering (SE) domain has not been well explored yet. As a result, many ML-powered software systems, particularly those utilized in the software engineering community, continue to be prone to fairness issues. Taking one of the typical SE tasks, i.e., code reviewer recommendation, as a subject, this paper conducts the first study toward investigating the issue of fairness of ML applications in the SE domain. Our empirical study demonstrates that current state-of-the-art ML-based code reviewer recommendation techniques exhibit unfairness and discriminating behaviors. Specifically, male reviewers get on average 7.25% more recommendations than female code reviewers compared to their distribution in the reviewer set. This paper also discusses the reasons why the studied ML-based code reviewer recommendation systems are unfair and provides solutions to mitigate the unfairness. Our study further indicates that the existing mitigation methods can enhance fairness by 100% in projects with a similar distribution of protected and privileged groups, but their effectiveness in improving fairness on imbalanced or skewed data is limited. Eventually, we suggest a solution to overcome the drawbacks of existing mitigation techniques and tackle bias in datasets that are imbalanced or skewed.
Unsupervised domain adaptation has recently emerged as an effective paradigm for generalizing deep neural networks to new target domains. However, there is still enormous potential to be tapped to reach the fully supervised performance. In this paper, we present a novel active learning strategy to assist knowledge transfer in the target domain, dubbed active domain adaptation. We start from an observation that energy-based models exhibit free energy biases when training (source) and test (target) data come from different distributions. Inspired by this inherent mechanism, we empirically reveal that a simple yet efficient energy-based sampling strategy sheds light on selecting the most valuable target samples than existing approaches requiring particular architectures or computation of the distances. Our algorithm, Energy-based Active Domain Adaptation (EADA), queries groups of targe data that incorporate both domain characteristic and instance uncertainty into every selection round. Meanwhile, by aligning the free energy of target data compact around the source domain via a regularization term, domain gap can be implicitly diminished. Through extensive experiments, we show that EADA surpasses state-of-the-art methods on well-known challenging benchmarks with substantial improvements, making it a useful option in the open world. Code is available at //github.com/BIT-DA/EADA.
小貼士
登錄享
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191