arXiv subjects

Peijun Zhang

Publications and source records attributed to Peijun Zhang.

5 recordsLinked to original sources

arXiv2026

PromptShield Home: Ambient Multimodal Prompt Injection Defense for Smart-Home Agents

Smart-home assistants increasingly use multimodal large language models (MLLMs) that perceive video and audio directly. This raises a safety question specific to the home: can the agent tell a genuine user command from ambient or externally-sourced content, television speech, on-screen text, or an overheard conversation, that merely looks like a command? We introduce PromptShield-Home, a pilot benchmark of realistic smart-home scenarios spanning addressee ambiguity, screen/audio injection, health-monitor false triggers, mixed occupancy, and a legitimate-command floor, and use it to compare three abstraction layers: traditional detectors (L0), a single MLLM agent (L1; vision, vision+ASR, and audio-visual), and multi-agent mediation (L2; voting, role specialists, cross-model arbitration). Because the label distribution is skewed toward inaction, aggregate accuracy is misleading, a constant always-block predictor scores 82%, so we report unsafe-execution and safe-completion rates separately. The two paradigms fail in opposite ways: detectors act on everything, while every MLLM configuration over-refuses, completing almost no genuine command and missing a true fall in every case. Crucially, their correct sets are disjoint: an oracle that always picks the right layer reaches 94.1%, against 76.5% for the best single layer. We report this as an upper bound, not a system - no router is implemented - and argue that home-agent safety is best served by learned routing and sensor fusion, not by replacing detectors with an MLLM.

cs.CR↗

arXiv2025

A novel boundary integrated neural networks for in plane fracture mechanics analysis of elastic and piezoelectric materials

In this study, we propose a novel approach, termed boundary integrated neural networks (BINNs), for analyzing in-plane crack problems within the framework of linear elastic fracture mechanics. The proposed approach integrates artificial neural networks (ANNs) with classical boundary integral equations (BIEs), enabling an efficient and accurate evaluation of partial differential equations (PDEs) associated with fracture mechanics. Additionally, novel special ANN-based crack-tip elements, the Special crack-tip Neural Networks(SPNNs) are developed to improve the modeling of displacement and stress fields in regions near crack tips. These specialized elements integrate the asymptotic characteristics of fracture mechanics into the neural network framework, ensuring enhanced accuracy in capturing the intricate singularities and steep gradients near the crack tips. Compared to conventional simulation tools in fracture mechanics, the present method offers several distinct advantages. First, by embedding higher-order fracture mechanics principles into the neural networks, the method achieves a more accurate and reliable representation of the near-tip fields, even when using relatively large crack-tip elements. Second, the SPNNs, which incorporates information about varying near-tip singularity orders, improve the method's versatility in solving problems involving complex and diverse crack-tips geometries. Moreover, the method demonstrates excellent computational efficiency due to the dimensionality reduction achieved by employing BIEs. Numerical experiments confirm that the proposed framework serves as a reliable, robust, and accurate tool for addressing fracture mechanics problems, offering substantial advantages over conventional numerical approaches.

cs.CE↗

arXiv2023

Boundary integrated neural networks (BINNs) for 2D elastostatic and piezoelectric problems: Theory and MATLAB code

In this paper, we make the first attempt to apply the boundary integrated neural networks (BINNs) for the numerical solution of two-dimensional (2D) elastostatic and piezoelectric problems. BINNs combine artificial neural networks with the well-established boundary integral equations (BIEs) to effectively solve partial differential equations (PDEs). The BIEs are utilized to map all the unknowns onto the boundary, after which these unknowns are approximated using artificial neural networks and resolved via a training process. In contrast to traditional neural network-based methods, the current BINNs offer several distinct advantages. First, by embedding BIEs into the learning procedure, BINNs only need to discretize the boundary of the solution domain, which can lead to a faster and more stable learning process (only the boundary conditions need to be fitted during the training). Second, the differential operator with respect to the PDEs is substituted by an integral operator, which effectively eliminates the need for additional differentiation of the neural networks (high-order derivatives of neural networks may lead to instability in learning). Third, the loss function of the BINNs only contains the residuals of the BIEs, as all the boundary conditions have been inherently incorporated within the formulation. Therefore, there is no necessity for employing any weighing functions, which are commonly used in traditional methods to balance the gradients among different objective functions. Moreover, BINNs possess the ability to tackle PDEs in unbounded domains since the integral representation remains valid for both bounded and unbounded domains. Extensive numerical experiments show that BINNs are much easier to train and usually give more accurate learning solutions as compared to traditional neural network-based methods.

cs.CE↗

arXiv2022

Enriched physics-informed neural networks for in-plane crack problems: Theory and MATLAB codes

In this paper, a method based on the physics-informed neural networks (PINNs) is presented to model in-plane crack problems in the linear elastic fracture mechanics. Instead of forming a mesh, the PINNs is meshless and can be trained on batches of randomly sampled collocation points. In order to capture the theoretical singular behavior of the near-tip stress and strain fields, the standard PINNs formulation is enriched here by including the crack-tip asymptotic functions such that the singular solutions at the crack-tip region can be modeled accurately without a high degree of nodal refinement. The learnable parameters of the enriched PINNs are trained to satisfy the governing equations of the cracked body and the corresponding boundary conditions. It was found that the incorporation of the crack-tip enrichment functions in PINNs is substantially simpler and more trouble-free than in the finite element (FEM) or boundary element (BEM) methods. The present algorithm is tested on a class of representative benchmarks with different modes of loading types. Results show that the present method allows the calculation of accurate stress intensity factors (SIFs) with far fewer degrees of freedom. A self-contained MATLAB code and data-sets accompanying this manuscript are also provided.

cs.CE↗

arXiv2016

In vitro protease cleavage and computer simulations reveal the HIV-1 capsid maturation pathway

HIV-1 virions assemble as immature particles containing Gag polyproteins that are processed by the viral protease into individual components, resulting in the formation of mature infectious particles. There are two competing models for the process of forming the mature HIV-1 core: the disassembly and de novo reassembly model and the non-diffusional displacive model. To study the maturation pathway, we simulate HIV-1 maturation in vitro by digesting immature particles and assembled virus-like particles with recombinant HIV-1 protease and monitor the process with biochemical assays and cryoEM structural analysis in parallel. Processing of Gag in vitro is accurate and efficient and results in both soluble capsid protein and conical or tubular capsid assemblies, seemingly converted from immature Gag particles. Computer simulations further reveal probable assembly pathways of HIV-1 capsid formation. Combining the experimental data and computer simulations, our results suggest a sequential combination of both displacive and disassembly/reassembly processes for HIV-1 maturation.

physics.bio-ph↗