Automation of test oracles is one of the most challenging facets of software testing, but remains comparatively less addressed compared to automated test input generation. Test oracles rely on a ground-truth that can distinguish between the correct and buggy behavior to determine whether a test fails (detects a bug) or passes. What makes the oracle problem challenging and undecidable is the assumption that the ground-truth should know the exact expected, correct, or buggy behavior. However, we argue that one can still build an accurate oracle without knowing the exact correct or buggy behavior, but how these two might differ. This paper presents SEER, a learning-based approach that in the absence of test assertions or other types of oracle, can determine whether a unit test passes or fails on a given method under test (MUT). To build the ground-truth, SEER jointly embeds unit tests and the implementation of MUTs into a unified vector space, in such a way that the neural representation of tests are similar to that of MUTs they pass on them, but dissimilar to MUTs they fail on them. The classifier built on top of this vector representation serves as the oracle to generate "fail" labels, when test inputs detect a bug in MUT or "pass" labels, otherwise. Our extensive experiments on applying SEER to more than 5K unit tests from a diverse set of open-source Java projects show that the produced oracle is (1) effective in predicting the fail or pass labels, achieving an overall accuracy, precision, recall, and F1 measure of 93%, 86%, 94%, and 90%, (2) generalizable, predicting the labels for the unit test of projects that were not in training or validation set with negligible performance drop, and (3) efficient, detecting the existence of bugs in only 6.5 milliseconds on average.
Synthetic data generation has been widely adopted in software testing, data privacy, imbalanced learning, and artificial intelligence explanation. In all such contexts, it is crucial to generate plausible data samples. A common assumption of approaches widely used for data generation is the independence of the features. However, typically, the variables of a dataset depend on one another, and these dependencies are not considered in data generation leading to the creation of implausible records. The main problem is that dependencies among variables are typically unknown. In this paper, we design a synthetic dataset generator for tabular data that can discover nonlinear causalities among the variables and use them at generation time. State-of-the-art methods for nonlinear causal discovery are typically inefficient. We boost them by restricting the causal discovery among the features appearing in the frequent patterns efficiently retrieved by a pattern mining algorithm. We design a framework for generating synthetic datasets with known causalities to validate our proposal. Broad experimentation on many synthetic and real datasets with known causalities shows the effectiveness of the proposed method.
Software testing activities scrutinize the artifacts and the behavior of a software product to find possible defects and ensure that the product meets its expected requirements. Recently, Deep Reinforcement Learning (DRL) has been successfully employed in complex testing tasks such as game testing, regression testing, and test case prioritization to automate the process and provide continuous adaptation. Practitioners can employ DRL by implementing from scratch a DRL algorithm or using a DRL framework. DRL frameworks offer well-maintained implemented state-of-the-art DRL algorithms to facilitate and speed up the development of DRL applications. Developers have widely used these frameworks to solve problems in various domains including software testing. However, to the best of our knowledge, there is no study that empirically evaluates the effectiveness and performance of implemented algorithms in DRL frameworks. Moreover, some guidelines are lacking from the literature that would help practitioners choose one DRL framework over another. In this paper, we empirically investigate the applications of carefully selected DRL algorithms on two important software testing tasks: test case prioritization in the context of Continuous Integration (CI) and game testing. For the game testing task, we conduct experiments on a simple game and use DRL algorithms to explore the game to detect bugs. Results show that some of the selected DRL frameworks such as Tensorforce outperform recent approaches in the literature. To prioritize test cases, we run experiments on a CI environment where DRL algorithms from different frameworks are used to rank the test cases. Our results show that the performance difference between implemented algorithms in some cases is considerable, motivating further investigation.
Context: Differential testing is a useful approach that uses different implementations of the same algorithms and compares the results for software testing. In recent years, this approach was successfully used for test campaigns of deep learning frameworks. Objective: There is little knowledge on the application of differential testing beyond deep learning. Within this article, we want to close this gap for classification algorithms. Method: We conduct a case study using Scikit-learn, Weka, Spark MLlib, and Caret in which we identify the potential of differential testing by considering which algorithms are available in multiple frameworks, the feasibility by identifying pairs of algorithms that should exhibit the same behavior, and the effectiveness by executing tests for the identified pairs and analyzing the deviations. Results: While we found a large potential for popular algorithms, the feasibility seems limited because often it is not possible to determine configurations that are the same in other frameworks. The execution of the feasible tests revealed that there is a large amount of deviations for the scores and classes. Only a lenient approach based on statistical significance of classes does not lead to a huge amount of test failures. Conclusions: The potential of differential testing beyond deep learning seems limited for research into the quality of machine learning libraries. Practitioners may still use the approach if they have deep knowledge about implementations, especially if a coarse oracle that only considers significant differences of classes is sufficient.
Latency and efficiency issues are often overlooked when evaluating IR models based on Pretrained Language Models (PLMs) in reason of multiple hardware and software testing scenarios. Nevertheless, efficiency is an important part of such systems and should not be overlooked. In this paper, we focus on improving the efficiency of the SPLADE model since it has achieved state-of-the-art zero-shot performance and competitive results on TREC collections. SPLADE efficiency can be controlled via a regularization factor, but solely controlling this regularization has been shown to not be efficient enough. In order to reduce the latency gap between SPLADE and traditional retrieval systems, we propose several techniques including L1 regularization for queries, a separation of document/query encoders, a FLOPS-regularized middle-training, and the use of faster query encoders. Our benchmark demonstrates that we can drastically improve the efficiency of these models while increasing the performance metrics on in-domain data. To our knowledge, {we propose the first neural models that, under the same computing constraints, \textit{achieve similar latency (less than 4ms difference) as traditional BM25}, while having \textit{similar performance (less than 10\% MRR@10 reduction)} as the state-of-the-art single-stage neural rankers on in-domain data}.
This paper investigates the parameter space of machine learning (ML) algorithms in aggravating or mitigating fairness bugs. Data-driven software is increasingly applied in social-critical applications where ensuring fairness is of paramount importance. The existing approaches focus on addressing fairness bugs by either modifying the input dataset or modifying the learning algorithms. On the other hand, the selection of hyperparameters, which provide finer controls of ML algorithms, may enable a less intrusive approach to influence the fairness. Can hyperparameters amplify or suppress discrimination present in the input dataset? How can we help programmers in detecting, understanding, and exploiting the role of hyperparameters to improve the fairness? We design three search-based software testing algorithms to uncover the precision-fairness frontier of the hyperparameter space. We complement these algorithms with statistical debugging to explain the role of these parameters in improving fairness. We implement the proposed approaches in the tool Parfait-ML (PARameter FAIrness Testing for ML Libraries) and show its effectiveness and utility over five mature ML algorithms as used in six social-critical applications. In these applications, our approach successfully identified hyperparameters that significantly improve (vis-a-vis the state-of-the-art techniques) the fairness without sacrificing precision. Surprisingly, for some algorithms (e.g., random forest), our approach showed that certain configuration of hyperparameters (e.g., restricting the search space of attributes) can amplify biases across applications. Upon further investigation, we found intuitive explanations of these phenomena, and the results corroborate similar observations from the literature.
With the growing capabilities of autonomous vehicles, there is a higher demand for sophisticated and pragmatic quality assurance approaches for machine learning-enabled systems in the automotive AI context. The use of simulation-based prototyping platforms provides the possibility for early-stage testing, enabling inexpensive testing and the ability to capture critical corner-case test scenarios. Simulation-based testing properly complements conventional on-road testing. However, due to the large space of test input parameters in these systems, the efficient generation of effective test scenarios leading to the unveiling of failures is a challenge. This paper presents a study on testing pedestrian detection and emergency braking system of the Baidu Apollo autonomous driving platform within the SVL simulator. We propose an evolutionary automated test generation technique that generates failure-revealing scenarios for Apollo in the SVL environment. Our approach models the input space using a generic and flexible data structure and benefits a multi-criteria safety-based heuristic for the objective function targeted for optimization. This paper presents the results of our proposed test generation technique in the 2021 IEEE Autonomous Driving AI Test Challenge. In order to demonstrate the efficiency and effectiveness of our approach, we also report the results from a baseline random generation technique. Our evaluation shows that the proposed evolutionary test case generator is more effective at generating failure-revealing test cases and provides higher diversity between the generated failures than the random baseline.
AI-based systems are software systems with functionalities enabled by at least one AI component (e.g., for image- and speech-recognition, and autonomous driving). AI-based systems are becoming pervasive in society due to advances in AI. However, there is limited synthesized knowledge on Software Engineering (SE) approaches for building, operating, and maintaining AI-based systems. To collect and analyze state-of-the-art knowledge about SE for AI-based systems, we conducted a systematic mapping study. We considered 248 studies published between January 2010 and March 2020. SE for AI-based systems is an emerging research area, where more than 2/3 of the studies have been published since 2018. The most studied properties of AI-based systems are dependability and safety. We identified multiple SE approaches for AI-based systems, which we classified according to the SWEBOK areas. Studies related to software testing and software quality are very prevalent, while areas like software maintenance seem neglected. Data-related issues are the most recurrent challenges. Our results are valuable for: researchers, to quickly understand the state of the art and learn which topics need more research; practitioners, to learn about the approaches and challenges that SE entails for AI-based systems; and, educators, to bridge the gap among SE and AI in their curricula.
Machine learning is nowadays a standard technique for data analysis within software applications. Software engineers need quality assurance techniques that are suitable for these new kinds of systems. Within this article, we discuss the question whether standard software testing techniques that have been part of textbooks since decades are also useful for the testing of machine learning software. Concretely, we try to determine generic and simple smoke tests that can be used to assert that basic functions can be executed without crashing. We found that we can derive such tests using techniques similar to equivalence classes and boundary value analysis. Moreover, we found that these concepts can also be applied to hyperparameters, to further improve the quality of the smoke tests. Even though our approach is almost trivial, we were able to find bugs in all three machine learning libraries that we tested and severe bugs in two of the three libraries. This demonstrates that common software testing techniques are still valid in the age of machine learning and that considerations how they can be adapted to this new context can help to find and prevent severe bugs, even in mature machine learning libraries.
The target of this paper is to present an industry-ready prototype software for general game playing. This software can also be used as the central element for experimental economics research, interfacing of game-theoretic libraries, AI-driven software testing, algorithmic trade, human behavior mining and simulation of (strategic) interactions. The software is based on a domain-specific language for electronic business to business negotiations -- SIDL3.0. The paper also contains many examples to prove the power of this language.
With the increasing adoption of Deep Neural Network (DNN) models as integral parts of software systems, efficient operational testing of DNNs is much in demand to ensure these models' actual performance in field conditions. A challenge is that the testing often needs to produce precise results with a very limited budget for labeling data collected in field. Viewing software testing as a practice of reliability estimation through statistical sampling, we re-interpret the idea behind conventional structural coverages as conditioning for variance reduction. With this insight we propose an efficient DNN testing method based on the conditioning on the representation learned by the DNN model under testing. The representation is defined by the probability distribution of the output of neurons in the last hidden layer of the model. To sample from this high dimensional distribution in which the operational data are sparsely distributed, we design an algorithm leveraging cross entropy minimization. Experiments with various DNN models and datasets were conducted to evaluate the general efficiency of the approach. The results show that, compared with simple random sampling, this approach requires only about a half of labeled inputs to achieve the same level of precision.
Generation-based fuzzing is a software testing approach which is able to discover different types of bugs and vulnerabilities in software. It is, however, known to be very time consuming to design and fine tune classical fuzzers to achieve acceptable coverage, even for small-scale software systems. To address this issue, we investigate a machine learning-based approach to fuzz testing in which we outline a family of test-case generators based on Recurrent Neural Networks (RNNs) and train those on readily available datasets with a minimum of human fine tuning. The proposed generators do, in contrast to previous work, not rely on heuristic sampling strategies but principled sampling from the predictive distributions. We provide a detailed analysis to demonstrate the characteristics and efficacy of the proposed generators in a challenging web browser testing scenario. The empirical results show that the RNN-based generators are able to provide better coverage than a mutation based method and are able to discover paths not discovered by a classical fuzzer. Our results supplement findings in other domains suggesting that generation based fuzzing with RNNs is a viable route to better software quality conditioned on the use of a suitable model selection/analysis procedure.