Search

Autonomous driving systems (ADS) are safety-critical and require comprehensive testing before their deployment on public roads. While existing testing approaches primarily aim at the criticality of scenarios, they often overlook the diversity of the generated scenarios that is also important to reflect system defects in different aspects. To bridge the gap, we propose LeGEND, that features a top-down fashion of scenario generation: it starts with abstract functional scenarios, and then steps downwards to logical and concrete scenarios, such that scenario diversity can be controlled at the functional level. However, unlike logical scenarios that can be formally described, functional scenarios are often documented in natural languages (e.g., accident reports) and thus cannot be precisely parsed and processed by computers. To tackle that issue, LeGEND leverages the recent advances of large language models (LLMs) to transform textual functional scenarios to formal logical scenarios. To mitigate the distraction of useless information in functional scenario description, we devise a two-phase transformation that features the use of an intermediate language; consequently, we adopt two LLMs in LeGEND, one for extracting information from functional scenarios, the other for converting the extracted information to formal logical scenarios. We experimentally evaluate LeGEND on Apollo, an industry-grade ADS from Baidu. Evaluation results show that LeGEND can effectively identify critical scenarios, and compared to baseline approaches, LeGEND exhibits evident superiority in diversity of generated scenarios. Moreover, we also demonstrate the advantages of our two-phase transformation framework, and the accuracy of the adopted LLMs.

We present a bounded model checking algorithm for signal temporal logic (STL) that exploits mixed-integer linear programming (MILP). A key technical element is our novel MILP encoding of the STL semantics; it follows the idea of stable partitioning from the recent work on SMT-based STL model checking. Assuming that our (continuous-time) system models can be encoded to MILP -- typical examples are rectangular hybrid automata (precisely) and hybrid dynamics with closed-form solutions (approximately) -- our MILP encoding yields an optimization-based model checking algorithm that is scalable, is anytime/interruptible, and accommodates parameter mining. Experimental evaluation shows our algorithm's performance advantages especially for complex STL formulas, demonstrating its practical relevance e.g. in the automotive domain., Comment: Extended version of the paper accepted by 36th International Conference on Computer-Aided Verification (CAV), 2024

Online monitoring is an effective validation approach for hybrid systems, that, at runtime, checks whether the (partial) signals of a system satisfy a specification in, e.g., Signal Temporal Logic (STL). The classic STL monitoring is performed by computing a robustness interval that specifies, at each instant, how far the monitored signals are from violating and satisfying the specification. However, since a robustness interval monotonically shrinks during monitoring, classic online monitors may fail in reporting new violations or in precisely describing the system evolution at the current instant. In this paper, we tackle these issues by considering the causation of violation or satisfaction, instead of directly using the robustness. We first introduce a Boolean causation monitor that decides whether each instant is relevant to the violation or satisfaction of the specification. We then extend this monitor to a quantitative causation monitor that tells how far an instant is from being relevant to the violation or satisfaction. We further show that classic monitors can be derived from our proposed ones. Experimental results show that the two proposed monitors are able to provide more detailed information about system evolution, without requiring a significantly higher monitoring cost., Comment: 31 pages, 7 figures, the full version of the paper accepted by CAV 2023

Cyber-Physical Systems (CPS) have been widely deployed in safety-critical domains such as transportation, power and energy. Recently, there comes an increasing demand in employing deep neural networks (DNNs) in CPS for more intelligent control and decision making in sophisticated industrial safety-critical conditions, giving birth to the class of DNN controllers. However, due to the inherent uncertainty and opaqueness of DNNs, concerns about the safety of DNN-enabled CPS are also surging. In this work, we propose an automated framework named AutoRepair that, given a safety requirement, identifies unsafe control behavior in a DNN controller and repairs them through an optimization-based method. Having an unsafe signal of system execution, AutoRepair iteratively explores the control decision space and searches for the optimal corrections for the DNN controller in order to satisfy the safety requirements. We conduct a comprehensive evaluation of AutoRepair on 6 instances of industry-level DNN-enabled CPS from different safety-critical domains. Evaluation results show that AutoRepair successfully repairs critical safety issues in the DNN controllers, and significantly improves the reliability of CPS.

The ability to drive a spin system to state far from the equilibrium is indispensable for investigating spin structures of antiferromagnets and their functional nonlinearities for spintronics. While optical methods have been considered for spin excitation, terahertz (THz) pulses appear to be a more convenient means of direct spin excitation without requiring coupling between spins and orbitals or phonons. However, room-temperature responses are usually limited to small deviations from the equilibrium state because of the relatively weak THz magnetic fields in common approaches. Here, we studied the magnetization dynamics in a HoFeO3 crystal at room temperature. A custom-made spiral-shaped microstructure was used to locally generate a strong multicycle THz magnetic near field perpendicular to the crystal surface; the maximum magnetic field amplitude of about 2 T was achieved. The observed time-resolved change in the Faraday ellipticity clearly showed second- and third-order harmonics of the magnetization oscillation and an asymmetric oscillation behaviour. Not only the ferromagnetic vector M but also the antiferromagnetic vector L plays an important role in the nonlinear dynamics of spin systems far from equilibrium.

The next era of program understanding is being propelled by the use of machine learning to solve software problems. Recent studies have shown surprising results of source code learning, which applies deep neural networks (DNNs) to various critical software tasks, e.g., bug detection and clone detection. This success can be greatly attributed to the utilization of massive high-quality training data, and in practice, data augmentation, which is a technique used to produce additional training data, has been widely adopted in various domains, such as computer vision. However, in source code learning, data augmentation has not been extensively studied, and existing practice is limited to simple syntax-preserved methods, such as code refactoring. Essentially, source code is often represented in two ways, namely, sequentially as text data and structurally as graph data, when it is used as training data in source code learning. Inspired by these analogy relations, we take an early step to investigate whether data augmentation methods that are originally used for text and graphs are effective in improving the training quality of source code learning. To that end, we first collect and categorize data augmentation methods in the literature. Second, we conduct a comprehensive empirical study on four critical tasks and 11 DNN architectures to explore the effectiveness of 12 data augmentation methods (including code refactoring and 11 other methods for text and graph data). Our results identify the data augmentation methods that can produce more accurate and robust models for source code learning, including those based on mixup (e.g., SenMixup for texts and Manifold-Mixup for graphs), and those that slightly break the syntax of source code (e.g., random swap and random deletion for texts).

Graph neural network (GNN)-based graph learning has been popular in natural language and programming language processing, particularly in text and source code classification. Typically, GNNs are constructed by incorporating alternating layers which learn transformations of graph node features, along with graph pooling layers that use graph pooling operators (e.g., Max-pooling) to effectively reduce the number of nodes while preserving the semantic information of the graph. Recently, to enhance GNNs in graph learning tasks, Manifold-Mixup, a data augmentation technique that produces synthetic graph data by linearly mixing a pair of graph data and their labels, has been widely adopted. However, the performance of Manifold-Mixup can be highly affected by graph pooling operators, and there have not been many studies that are dedicated to uncovering such affection. To bridge this gap, we take an early step to explore how graph pooling operators affect the performance of Mixup-based graph learning. To that end, we conduct a comprehensive empirical study by applying Manifold-Mixup to a formal characterization of graph pooling based on 11 graph pooling operations (9 hybrid pooling operators, 2 non-hybrid pooling operators). The experimental results on both natural language datasets (Gossipcop, Politifact) and programming language datasets (JAVA250, Python800) demonstrate that hybrid pooling operators are more effective for Manifold-Mixup than the standard Max-pooling and the state-of-the-art graph multiset transformer (GMT) pooling, in terms of producing more accurate and robust GNN models., Comment: Accepted by Journal of Systems and Software (JSS) 2024

Inspired by the great success of Deep Neural Networks (DNNs) in natural language processing (NLP), DNNs have been increasingly applied in source code analysis and attracted significant attention from the software engineering community. Due to its data-driven nature, a DNN model requires massive and high-quality labeled training data to achieve expert-level performance. Collecting such data is often not hard, but the labeling process is notoriously laborious. The task of DNN-based code analysis even worsens the situation because source code labeling also demands sophisticated expertise. Data augmentation has been a popular approach to supplement training data in domains such as computer vision and NLP. However, existing data augmentation approaches in code analysis adopt simple methods, such as data transformation and adversarial example generation, thus bringing limited performance superiority. In this paper, we propose a data augmentation approach MIXCODE that aims to effectively supplement valid training data, inspired by the recent advance named Mixup in computer vision. Specifically, we first utilize multiple code refactoring methods to generate transformed code that holds consistent labels with the original data. Then, we adapt the Mixup technique to mix the original code with the transformed code to augment the training data. We evaluate MIXCODE on two programming languages (Java and Python), two code tasks (problem classification and bug detection), four benchmark datasets (JAVA250, Python800, CodRep1, and Refactory), and seven model architectures (including two pre-trained models CodeBERT and GraphCodeBERT). Experimental results demonstrate that MIXCODE outperforms the baseline data augmentation approach by up to 6.24% in accuracy and 26.06% in robustness., Comment: Accepted by SANER 2023

Automated Driving Systems (ADS) have made great achievements in recent years thanks to the efforts from both academia and industry. A typical ADS is composed of multiple modules, including sensing, perception, planning, and control, which brings together the latest advances in different domains. Despite these achievements, safety assurance of ADS is of great significance, since unsafe behavior of ADS can bring catastrophic consequences. Testing has been recognized as an important system validation approach that aims to expose unsafe system behavior; however, in the context of ADS, it is extremely challenging to devise effective testing techniques, due to the high complexity and multidisciplinarity of the systems. There has been great much literature that focuses on the testing of ADS, and a number of surveys have also emerged to summarize the technical advances. Most of the surveys focus on the system-level testing performed within software simulators, and they thereby ignore the distinct features of different modules. In this paper, we provide a comprehensive survey on the existing ADS testing literature, which takes into account both module-level and system-level testing. Specifically, we make the following contributions: (1) we survey the module-level testing techniques for ADS and highlight the technical differences affected by the features of different modules; (2) we also survey the system-level testing techniques, with focuses on the empirical studies that summarize the issues occurring in system development or deployment, the problems due to the collaborations between different modules, and the gap between ADS testing in simulators and the real world; (3) we identify the challenges and opportunities in ADS testing, which pave the path to the future research in this field.

Cyber-physical systems (CPS) have been broadly deployed in safety-critical domains, such as automotive systems, avionics, medical devices, etc. In recent years, Artificial Intelligence (AI) has been increasingly adopted to control CPS. Despite the popularity of AI-enabled CPS, few benchmarks are publicly available. There is also a lack of deep understanding on the performance and reliability of AI-enabled CPS across different industrial domains. To bridge this gap, we initiate to create a public benchmark of industry-level CPS in seven domains and build AI controllers for them via state-of-the-art deep reinforcement learning (DRL) methods. Based on that, we further perform a systematic evaluation of these AI-enabled systems with their traditional counterparts to identify the current challenges and explore future opportunities. Our key findings include (1) AI controllers do not always outperform traditional controllers, (2) existing CPS testing techniques (falsification, specifically) fall short of analyzing AI-enabled CPS, and (3) building a hybrid system that strategically combines and switches between AI controllers and traditional controllers can achieve better performance across different domains. Our results highlight the need for new testing techniques for AI-enabled CPS and the need for more investigations into hybrid CPS systems to achieve optimal performance and reliability.

Falsification of hybrid systems is attracting ever-growing attention in quality assurance of Cyber-Physical Systems (CPS) as a practical alternative to exhaustive formal verification. In falsification, one searches for a falsifying input that drives a given black-box model to output an undesired signal. In this paper, we identify input constraints---such as the constraint "the throttle and brake pedals should not pressed simultaneously" for an automotive powertrain model---as a key factor for the practical value of falsification methods. We propose three approaches for systematically addressing input constraints in optimization-based falsification, two among which come from the lexicographic method studied in the context of constrained multi-objective optimization. Our experiments show the approaches' effectiveness., Comment: Accepted by 12th NASA Formal Methods Symposium (NFM 2020)