YWYuhui Wang

Yuhui Wang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yuhui Wang has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Safeguarding LLM Agents against Long-Horizon Threats via Shadow Memory

    by Yuhui Wang, Tanqiu Jiang, Jiacheng Liang, Charles Fleming, Ting Wang

    As large language model (LLM)-powered agents are increasingly deployed to perform complex, real-world tasks, they face a growing class of attacks that exploit extended user–agent–environment interactions to pursue malicious objectives improbable in single-turn settings. Such long-horizon threats pose significant risks to the safe deployment of LLM agents in critical domains. In this paper, we present ShadowMem, a novel defensive framework designed to counter a wide range of long-horizon threats. Inspired by the ''shadow stack'' abstraction in systems security, ShadowMem maintains a dedicated, safety-focused agentic memory that distills and retains safety-critical context across the agent's full execution trajectory, leveraging this shadow memory to proactively assess the risk of pending actions prior to their execution. Extensive evaluation demonstrates that ShadowMem substantially outperforms existing defenses across diverse long-horizon threats in detection accuracy, achieves early-stage detection for the majority of attacks, and introduces only negligible overhead to agent utility. To our best knowledge, ShadowMem represents the first framework to detect and mitigate long-horizon threats using an agentic memory approach, establishing a new paradigm for this critical challenge and opening promising directions for future research.

  • Deep Learning-Based Sensor Selection for Failure Mode Recognition and Prognostics Under Time-Varying Operating Conditions

    by Yuhui Wang, Andi Wang, Di Wang, Dong Wang

    Failure mode (FM) recognition and remaining useful lifetime (RUL) prediction play pivotal roles in the field of prognostics and health management (PHM), particularly in regard to monitoring machinery degradation. Advances in sensor technology have opened avenues for FM recognition and RUL prediction by leveraging data from multiple sensors. However, previous research has exhibited certain limitations. Some studies have taken all multisensor data as direct inputs, overlooking the potential heterogeneity in the relevance of individual sensor data to machinery degradation. Others have relied on visual inspection and subjective assessments for sensor selection. These approaches struggle to adaptively select sensors, especially in scenarios involving multiple FMs and operating conditions (OCs), and when only partial FM labels are available. To address these challenges, this paper proposes a novel deep-learning network that adaptively selects sensors to jointly recognize FMs and predict RUL under time-varying OCs. The core of this network incorporates an attention-based long short-term memory (LSTM) module. Within this module, adaptive sensor selection weights are generated, leading to the accurate recognition of FMs and the precise prediction of the RUL. In the context of model training, we construct loss functions utilizing semilabeled samples and extract OC-invariant features through domain adaptation, enhancing the accuracy of FM recognition and RUL prediction. To assess the effectiveness and the generalizability of the proposed method, numerical experiments and two case studies involving aircraft engines and bearings are conducted Note to Practitioners —This paper proposes a deep-learning network designed for adaptive sensor selection in the context of semisupervised FM recognition and RUL prediction, particularly in scenarios involving multiple OCs. To operationalize this method, five key steps are outlined: First, Data Collection: data are gathered from multiple sensors, time-varying OCs, multiple FMs, and failure time of historical units. It is important to note that FM data are available for only a subset of historical units. Second, Data Preprocessing: The sensor data are tailored using the sliding time window technique, generating a substantial number of samples from historical units. Third, Network Construction: Subsequently, the adaptive sensor selection network is constructed. Fourth, Model Training: Loss functions are constructed, and model parameters are estimated through end-to-end training. Finally, Model Application: The method is utilized to recognize FMs and predict RUL for in-service units. This deep learning network can be applied effectively to various degraded machines experiencing multiple FMs and OCs. It is particularly suitable for machines with complex physical mechanisms or unknown failure thresholds.


  • A Latent Variable-Based Multitask Learning Approach for Degradation Modeling of Machines With Dependency and Heterogeneity

    by Di Wang, Yuhui Wang, Xiaochen Xian

    Remaining useful lifetime (RUL) prediction based on degradation signals of sensors is of critical importance in prognostics and health management (PHM) of machines in manufacturing systems. The machines are often under the same operational and environmental condition and thus show dependent but heterogeneous degradation profiles. However, many existing studies ignored these characteristics among machines, leading to poor RUL prediction results especially when missing data exists. To address this issue, this paper develops a latent variable-based multi-task learning (LVMTL) approach for degradation modeling and prognostics of machines based on multiple sensor signals. Specifically, we first adopt a polynomial model to fit the degradation processes of machines’ health indices (HIs), which are estimated based on multiple sensor signals. Taking the HIs as latent variables, we develop an LVMTL model aiming to capture the dependency and heterogeneity among machines. For parameter estimation, we develop a unique iterated quadratic optimization-integrated expectation-maximum (QOIEM) algorithm that updates model parameters via quadratic programming (QP) and maximum a posteriori-based expectation-maximum (MAP-EM) considering the principles for estimating an HI. The QOIEM has been proven to have satisfactory convergence performance in theory in this study. Numerical experiments and a real case study on aircraft turbine engines have been implemented to compare the prognosis performance and robustness of incomplete datasets for the proposed and benchmark methods.