Jie M. Zhang, Mark Harman, Lei Ma, Yang Liu
This paper provides a comprehensive survey of Machine Learning Testing (ML testing) research. It covers 144 papers on testing properties (e.g., correctness, robustness, and fairness), testing components (e.g., the data, learning program, and framework), testing workflow (e.g., test generation and test evaluation), and application scenarios (e.g., autonomous driving, machine translation). The paper also analyses trends concerning datasets, research trends, and research focus, concluding with research challenges and promising research directions in ML testing.
Da Song, Xuan Xie, Jiayang Song, Derui Zhu, Yuheng Huang, Felix Juefei-Xu, Lei Ma
Over the past decade, Artificial Intelligence (AI) has had great success recently and is being used in a wide range of academic and industrial fields. More recently, LLMs have made rapid advancements that have propelled AI to a new level, enabling even more diverse applications and industrial domains with intelligence, particularly in areas like software engineering and natural language processing. Nevertheless, a number of emerging trustworthiness concerns and issues exhibited in LLMs have already recently received much attention, without properly solving which the widespread adoption of LLMs could be greatly hindered in practice. The distinctive characteristics of LLMs, such as the self-attention mechanism, extremely large model scale, and autoregressive generation schema, differ from classic AI software based on CNNs and RNNs and present new challenges for quality analysis. Up to the present, it still lacks universal and systematic analysis techniques for LLMs despite the urgent industrial demand. Towards bridging this gap, we initiate an early exploratory study and propose a universal analysis framework for LLMs, LUNA, designed to be general and extensible, to enable versatile analysis of LLMs from multiple quality perspectives in a human-interpretable manner. In particular, we first leverage the data from desired trustworthiness perspectives to construct an abstract model as an auxiliary analysis asset, which is empowered by various abstract model construction methods. To assess the quality of the abstract model, we collect and define a number of evaluation metrics, aiming at both abstract model level and the semantics level. Then, the semantics, which is the degree of satisfaction of the LLM w.r.t. the trustworthiness perspective, is bound to and enriches the abstract model with semantics, which enables more detailed analysis applications for diverse purposes.
Lei Ma, Felix Juefei-Xu, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Chunyang Chen, Ting Su, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang
Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good accuracy performance on test data can hardly provide confidence to the testing adequacy and generality of DL systems. Unlike traditional software systems that have clear and controllable logic and functionality, the lack of interpretability in a DL system makes system analysis and defect detection difficult, which could potentially hinder its real-world deployment. In this paper, we propose DeepGauge, a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed. The in-depth evaluation of our proposed testing criteria is demonstrated on two well-known datasets, five DL systems, and with four state-of-the-art adversarial attack techniques against DL. The potential usefulness of DeepGauge sheds light on the construction of more generic and robust DL systems.
Lei Ma, Ling Guo, Hao Wu, Tao Zhou
Learning operators from data is central to scientific machine learning. While DeepONets are widely used for their ability to handle complex domains, they require fixed sensor numbers and locations, lack mechanisms for uncertainty quantification (UQ), and are thus limited in practical applicability. Recent permutationinvariant extensions, such as the Variable-Input Deep Operator Network (VIDON), relax these sensor constraints but still rely on sufficiently dense observations and cannot capture uncertainties arising from incomplete measurements or from operators with inherent randomness. To address these challenges, we propose UQ-SONet, a permutation-invariant operator learning framework with built-in UQ. Our model integrates a set transformer embedding to handle sparse and variable sensor locations, and employs a conditional variational autoencoder (cVAE) to approximate the conditional distribution of the solution operator. By minimizing the negative ELBO, UQ-SONet provides principled uncertainty estimation while maintaining predictive accuracy. Numerical experiments on deterministic and stochastic PDEs, including the Navier-Stokes equation, demonstrate the robustness and effectiveness of the proposed framework.
Yao Su, Zhentian Qian, Lei Ma, Lifang He, Xiangnan Kong
Brain extraction, registration and segmentation are indispensable preprocessing steps in neuroimaging studies. The aim is to extract the brain from raw imaging scans (i.e., extraction step), align it with a target brain image (i.e., registration step) and label the anatomical brain regions (i.e., segmentation step). Conventional studies typically focus on developing separate methods for the extraction, registration and segmentation tasks in a supervised setting. The performance of these methods is largely contingent on the quantity of training samples and the extent of visual inspections carried out by experts for error correction. Nevertheless, collecting voxel-level labels and performing manual quality control on high-dimensional neuroimages (e.g., 3D MRI) are expensive and time-consuming in many medical studies. In this paper, we study the problem of one-shot joint extraction, registration and segmentation in neuroimaging data, which exploits only one labeled template image (a.k.a. atlas) and a few unlabeled raw images for training. We propose a unified end-to-end framework, called JERS, to jointly optimize the extraction, registration and segmentation tasks, allowing feedback among them. Specifically, we use a group of extraction, registration and segmentation modules to learn the extraction mask, transformation and segmentation mask, where modules are interconnected and mutually reinforced by self-supervision. Empirical results on real-world datasets demonstrate that our proposed method performs exceptionally in the extraction, registration and segmentation tasks. Our code and data can be found at https://github.com/Anonymous4545/JERS
Alvin Chan, Lei Ma, Felix Juefei-Xu, Xiaofei Xie, Yang Liu, Yew Soon Ong
Deep neural networks (DNN), while becoming the driving force of many novel technology and achieving tremendous success in many cutting-edge applications, are still vulnerable to adversarial attacks. Differentiable neural computer (DNC) is a novel computing machine with DNN as its central controller operating on an external memory module for data processing. The unique architecture of DNC contributes to its state-of-the-art performance in tasks which requires the ability to represent variables and data structure as well as to store data over long timescales. However, there still lacks a comprehensive study on how adversarial examples affect DNC in terms of robustness. In this paper, we propose metamorphic relation based adversarial techniques for a range of tasks described in the natural processing language domain. We show that the near-perfect performance of the DNC in bAbI logical question answering tasks can be degraded by adversarially injected sentences. We further perform in-depth study on the role of DNC's memory size in its robustness and analyze the potential reason causing why DNC fails. Our study demonstrates the current challenges and potential opportunities towards constructing more robust DNCs.
Xiaofei Xie, Lei Ma, Felix Juefei-Xu, Hongxu Chen, Minhui Xue, Bo Li, Yang Liu, Jianjun Zhao, Jianxiong Yin, Simon See
In company with the data explosion over the past decade, deep neural network (DNN) based software has experienced unprecedented leap and is becoming the key driving force of many novel industrial applications, including many safety-critical scenarios such as autonomous driving. Despite great success achieved in various human intelligence tasks, similar to traditional software, DNNs could also exhibit incorrect behaviors caused by hidden defects causing severe accidents and losses. In this paper, we propose DeepHunter, an automated fuzz testing framework for hunting potential defects of general-purpose DNNs. DeepHunter performs metamorphic mutation to generate new semantically preserved tests, and leverages multiple plugable coverage criteria as feedback to guide the test generation from different perspectives. To be scalable towards practical-sized DNNs, DeepHunter maintains multiple tests in a batch, and prioritizes the tests selection based on active feedback. The effectiveness of DeepHunter is extensively investigated on 3 popular datasets (MNIST, CIFAR-10, ImageNet) and 7 DNNs with diverse complexities, under a large set of 6 coverage criteria as feedback. The large-scale experiments demonstrate that DeepHunter can (1) significantly boost the coverage with guidance; (2) generate useful tests to detect erroneous behaviors and facilitate the DNN model quality evaluation; (3) accurately capture potential defects during DNN quantization for platform migration.
Lei Ma, Fuyuan Zhang, Jiyuan Sun, Minhui Xue, Bo Li, Felix Juefei-Xu, Chao Xie, Li Li, Yang Liu, Jianjun Zhao, Yadong Wang
Deep learning (DL) defines a new data-driven programming paradigm where the internal system logic is largely shaped by the training data. The standard way of evaluating DL models is to examine their performance on a test dataset. The quality of the test dataset is of great importance to gain confidence of the trained models. Using an inadequate test dataset, DL models that have achieved high test accuracy may still lack generality and robustness. In traditional software testing, mutation testing is a well-established technique for quality evaluation of test suites, which analyzes to what extent a test suite detects the injected faults. However, due to the fundamental difference between traditional software and deep learning-based software, traditional mutation testing techniques cannot be directly applied to DL systems. In this paper, we propose a mutation testing framework specialized for DL systems to measure the quality of test data. To do this, by sharing the same spirit of mutation testing in traditional software, we first define a set of source-level mutation operators to inject faults to the source of DL (i.e., training data and training programs). Then we design a set of model-level mutation operators that directly inject faults into DL models without a training process. Eventually, the quality of test data could be evaluated from the analysis on to what extent the injected faults could be detected. The usefulness of the proposed mutation testing techniques is demonstrated on two public datasets, namely MNIST and CIFAR-10, with three DL models.
Lei Ma, Jincong Han, Zhaoxin Wang, Dian Zhang
Large-scale multimodal language models (LMMs) have achieved remarkable success in general domains. However, the exploration of diagnostic language models based on multimodal cephalometric medical data remains limited. In this paper, we propose a novel multimodal cephalometric analysis and diagnostic dialogue model. Firstly, a multimodal orthodontic medical dataset is constructed, comprising cephalometric images and doctor-patient dialogue data, with automatic analysis of cephalometric landmarks using U-net and generation of diagnostic reports. Then, the cephalometric dataset and generated diagnostic reports are separately fine-tuned on Minigpt-4 and VisualGLM. Results demonstrate that the CephGPT-4 model exhibits excellent performance and has the potential to revolutionize orthodontic measurement and diagnostic applications. These innovations hold revolutionary application potential in the field of orthodontics.
Lei Ma, Riguo Mei, Mengmeng Liu, Xuxin Zhao, Qixing Wu, Hongyuan Sun
Prior experimental studies showed that nanowires are promising structures for improving the thermoelectric performance of practical thermoelectric materials due to the strongly induced phonon-boundary scattering. However, few studies examined the impact of phonon-boundary scattering on the thermal conductivity of thermoelectric nanowires from a first-principle approach. In this work, we systematically study the role of phonon-boundary scattering with different boundary specularities on the thermal conductivity of PbSe nanowires by rigorously solving the full phonon Boltzmann transport equation without any adjustable parameters. We observe significant thermal conductivity reduction for rough PbSe nanowires with diameters less than a few hundred nanometers. The reduction reaches ~ 40% for 10 nm thick rough PbSe nanowires at room temperature. The diameter-dependent thermal conductivities are found to contain important information about the phonon mean free path distribution from a standard reconstruction algorithm. The simulation results are important for fundamental understanding of nanoscale thermal transport in thermoelectric materials and will guide future design of thermoelectric devices to achieve better energy conversion efficiency.
Olga Poppe, Chuan Lei, Lei Ma, Allison Rozet, Elke A. Rundensteiner
Complex event processing (CEP) systems continuously evaluate large workloads of pattern queries under tight time constraints. Event trend aggregation queries with Kleene patterns are commonly used to retrieve summarized insights about the recent trends in event streams. State-of-art methods are limited either due to repetitive computations or unnecessary trend construction. Existing shared approaches are guided by statically selected and hence rigid sharing plans that are often sub-optimal under stream fluctuations. In this work, we propose a novel framework Hamlet that is the first to overcome these limitations. Hamlet introduces two key innovations. First, Hamlet adaptively decides whether to share or not to share computations depending on the current stream properties at run time to harvest the maximum sharing benefit. Second, Hamlet is equipped with a highly efficient shared trend aggregation strategy that avoids trend construction. Our experimental study on both real and synthetic data sets demonstrates that Hamlet consistently reduces query latency by up to five orders of magnitude compared to the state-of-the-art approaches.
Lei Ma, Jinyang Liu, Tieying Zhang, Peter M. VanNostrand, Dennis M. Hofmann, Lei Cao, Elke A. Rundensteiner, Jianjun Chen
Log anomaly detection is crucial for uncovering system failures and security risks. Although logs originate from nested component executions with clear boundaries, this structure is lost when stored as flat sequences. As a result, state-of-the-art methods often miss true dependencies within executions while learning spurious correlations across unrelated events. We propose KRONE, the first hierarchical anomaly detection framework that automatically derives execution hierarchies from flat logs to enable modular, multi-level anomaly detection. At its core, the KRONE Log Abstraction Model extracts application-specific semantic hierarchies, which are used to recursively decompose log sequences into coherent execution units, referred to as KRONE Seqs. This transforms sequence-level detection into a set of modular KRONE Seq-level detection tasks. For each test KRONE Seq, KRONE adopts a hybrid modular detection strategy that routes between an efficient level-independent Local-Context detector for rapid filtering and a Nested-Aware detector that captures cross-level semantic dependencies, augmented with LLM-based anomaly detection and explanation. KRONE further optimizes detection through cached result reuse and early-exit strategies along the hierarchy. Experiments on three public benchmarks and one industrial dataset from ByteDance Cloud demonstrate that KRONE achieves substantial improvements in accuracy (42.49% to 87.98%), F1 score, data efficiency (117.3x reduction), resource efficiency (43.7x reduction), and interpretability. KRONE improves F1-score by 10.07% (82.76% to 92.83%) over prior methods while reducing LLM usage to only 1.1% to 3.3% of the test data. Code: https://github.com/LeiMa0324/KRONE Demo: https://leima0324.github.io/KRONE_Demo_official/
Lei Ma, Ke Guan, Dong Yan, Danping He, Nuno R. Leonor, Bo Ai, Junhyeong Kim
The integration of satellite and terrestrial communication systems plays a vital role in the fifth-generation mobile communication system (5G) for the ubiquitous coverage, reliable service and flexible networking. Moreover, the millimeter wave (mmWave) communication with large bandwidth is a key enabler for 5G intelligent rail transportation. In this paper, the satellite-terrestrial channel at 22.6 GHz is characterized for a typical high-speed railway (HSR) environment. The three-dimensional model of the railway scenario is reconstructed and imported into the Cloud Ray-Tracing (CloudRT) simulation platform. Based on extensive ray-tracing simulations, the channel for the terrestrial HSR system and the satellite-terrestrial system with two weather conditions are characterized, and the interference between them are evaluated. The results of this paper can help for the design and evaluation for the satellite-terrestrial communication system enabling future intelligent rail transportation.
Lei Ma, Tian-Yi Wang, Chunjing Xie
This paper considers the low Mach number limit and far field convergence rates of steady Euler flows with external forces in three-dimensional infinitely long nozzles with an obstacle inside. First, the well-posedness theory for both incompressible and compressible subsonic flows with external forces in multidimensional nozzle with an obstacle inside are established by several uniform estimates. The uniformly subsonic compressible flows tend to the incompressible flows as quadratic order of Mach number as the compressibility parameter goes to zero. Furthermore, we also give the convergence rates of both incompressible flow and compressible flow at far fields as the boundary of nozzle goes to flat even when the forces do not admit convergence rate at far fields. The convergence rates obtained for the flows at far fields clearly describe the effects of the external force.
Xiaoning Du, Xiaofei Xie, Yi Li, Lei Ma, Jianjun Zhao, Yang Liu
Deep learning (DL) defines a data-driven programming paradigm that automatically composes the system decision logic from the training data. In company with the data explosion and hardware acceleration during the past decade, DL achieves tremendous success in many cutting-edge applications. However, even the state-of-the-art DL systems still suffer from quality and reliability issues. It was only until recently that some preliminary progress was made in testing feed-forward DL systems. In contrast to feed-forward DL systems, recurrent neural networks (RNN) follow a very different architectural design, implementing temporal behaviors and memory with loops and internal states. Such stateful nature of RNN contributes to its success in handling sequential inputs such as audio, natural languages and video processing, but also poses new challenges for quality assurance. In this paper, we initiate the very first step towards testing RNN-based stateful DL systems. We model RNN as an abstract state transition system, based on which we define a set of test coverage criteria specialized for stateful DL systems. Moreover, we propose an automated testing framework, DeepCruiser, which systematically generates tests in large scale to uncover defects of stateful DL systems with coverage guidance. Our in-depth evaluation on a state-of-the-art speech-to-text DL system demonstrates the effectiveness of our technique in improving quality and reliability of stateful DL systems.
Lei Ma, Fuyuan Zhang, Minhui Xue, Bo Li, Yang Liu, Jianjun Zhao, Yadong Wang
Deep learning (DL) has achieved remarkable progress over the past decade and been widely applied to many safety-critical applications. However, the robustness of DL systems recently receives great concerns, such as adversarial examples against computer vision systems, which could potentially result in severe consequences. Adopting testing techniques could help to evaluate the robustness of a DL system and therefore detect vulnerabilities at an early stage. The main challenge of testing such systems is that its runtime state space is too large: if we view each neuron as a runtime state for DL, then a DL system often contains massive states, rendering testing each state almost impossible. For traditional software, combinatorial testing (CT) is an effective testing technique to reduce the testing space while obtaining relatively high defect detection abilities. In this paper, we perform an exploratory study of CT on DL systems. We adapt the concept in CT and propose a set of coverage criteria for DL systems, as well as a CT coverage guided test generation technique. Our evaluation demonstrates that CT provides a promising avenue for testing DL systems. We further pose several open questions and interesting directions for combinatorial testing of DL systems.
Lei Ma, Riguo Mei, Mengmeng Liu, Xuxin Zhao, Qixing Wu, Hongyuan Sun
Non-diffusive thermal transport has gained extensive research interest recently due to its important implications on fundamental understanding of material phonon mean free path distributions and many nanoscale energy applications. In this work, we systematically investigate the role of boundary scattering and nanowire length on the nondiffusive thermal transport in thin silicon nanowires by rigorously solving the phonon Boltzmann transport equation using a variance reduced Monte Carlo technique across a range of temperatures. The simulations use the complete phonon dispersion and spectral lifetime data obtained from first-principle density function theory calculations as input without any adjustable parameters. Our BTE simulation results show that the nanowire length plays an important role in determining the thermal conductivity of silicon nanowires. In addition, our simulation results suggest significant phonon confinement effect for the previously measured silicon nanowires. These findings are important for a comprehensive understanding of microscopic non-diffusive thermal transport in silicon nanowires.
Lei Mao, Jong Ho Lee, Yasmeen Faroqi Shah, Stephanie Valencia
AI offers key advantages such as instant generation, multi-modal support, and personalized adaptability - potential that can address the highly heterogeneous communication barriers faced by people with aphasia (PWAs). We designed AI-enhanced communication tools and used them as design probes to explore how AI's real-time processing and generation capabilities - across text, image, and audio - can align with PWAs' needs in real-time communication and preparation for future conversations respectively. Through a two-phase "Research through Design" approach, eleven PWAs contributed design insights and evaluated four AI-enhanced prototypes. These prototypes aimed to improve communication grounding and conversational agency through visual verification, grammar construction support, error correction, and reduced language processing load. Despite some challenges, such as occasional mismatches with user intent, findings demonstrate how AI's specific capabilities can be advantageous in addressing PWAs' complex needs. Our work contributes design insights for future Augmentative and Alternative Communication (AAC) systems.
Lei Ma
We present a concise dynamical picture of infant-driven household chaos. The framework has three postulations: recurrent daily chaos, overall entropy growth in household organization, and transient local ordering episodes with switching rules (a volatile Maxwell-demon effect). We illustrate entropy growth with a two-region toy model (organizer vs. play area), where entropy production is nonnegative and long-time behavior is typically play-area dominated. We also model toy diffusion and curiosity-driven behavior, where novelty matters more than punishment in the short term, while gradual learning still occurs.
Lei Ma, Shashank Shalgar, Huaiyu Duan
We consider the flavor transformation of neutrinos through oscillatory matter profiles. We show that the neutrino oscillation Hamiltonian in this case describes a Rabi system with an infinite number of Rabi modes. We further show that, in a given physics problem, the majority of the Rabi modes have too small amplitudes to be relevant. We also go beyond the rotating wave approximation and derive the relative detuning of the Rabi resonance when multiple Rabi modes with small amplitudes are present. We provide an explicit criterion of whether an off-resonance Rabi mode can affect the parametric flavor transformation of the neutrino.