ZZZhentong Zhang

Zhentong Zhang

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Zhentong Zhang has a total of 24 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    Boosting Learning Efficiency in Few-Shot Tasks With Layer-Adaptive PID Control

    by Pengfei Zhang, Xinde Li, Le Yu, Zhentong Zhang, Fir Dunkin, Huaping Liu, Zhijun Li

    Few-shot learning seeks to recognize novel classes from limited examples. Model-agnostic meta-learning (MAML), known for its simplicity and flexibility, learns an effective initialization for fast adaptation in data-scarce settings. However, MAML-based methods face challenges when there is a significant distributional shift between training and testing tasks, leading to inefficient learning and poor generalization across domains. In this work, we identify the core issues: inflexible weight update rules and limited adaptive learning capabilities. Instead of focusing solely on better initialization, we aim to enhance the adaptation process. Consequently, we propose a novel Layer-Adaptive Proportional-Integral-Derivative (LA-PID) optimizer integrated into a meta-learning framework. This design incorporates classical control theory, utilizing PID control to dynamically adjust task-specific gains at each network layer. Additionally, the theoretical conditions for optimal hyperparameter initialization and global model convergence are addressed from both control and optimization perspectives. Experiments on benchmark datasets show that LA-PID achieves state-of-the-art performance in few-shot classification, cross-domain, and regression tasks, while requiring fewer training steps.


  • CAIS: Fine-Grained Controllable Adversarial Attacks for Instance Segmentation in Uncrewed Systems

    by Zhentong Zhang, Xinde Li, Hongwei Sun, Guoliang Wu, Le Yu, Zhijun Li

    The threat of adversarial attacks on artificial intelligence in uncrewed systems has raised significant concerns regarding security. At a finer granularity, target-level adversarial attacks in instance segmentation play a critical role. However, existing methods are limited to generating disordered pixel perturbations, making it difficult to precisely control the attack targets. To address this challenge, a novel controllable attack for instance segmentation (CAIS) is proposed. CAIS precisely manipulates foreground targets while avoiding misleading the background, thereby enhancing the stealthiness of the attack. Specifically, CAIS introduces a focal gradient enhancement method to guide the victim detector to focus on foreground regions, strengthening the gradient signals for adversarial attacks. In addition, we design an attention guided perturbation method, which reduces the interference of background information through adaptive foreground–background gradient separation. This article introduces a dual loop asynchronous optimization strategy, integrating the aforementioned methods into the CAIS attack. Extensive experiments demonstrate that CAIS achieves superior attack performance on victim instance regions while maintaining prediction consistency in nonvictim regions. Consequently, this advancement will inspire the design of adversarial threat detection and defense mechanisms, ultimately contributing to the safety and reliability of uncrewed systems.

  • AttackTracer: Semantic-level adversarial attack location traceability via evidential diffusion model

    by Zhentong Zhang, Xinde Li, Pengfei Zhang, Kui Wang, Tianrong Gao, Tao Shen


  • From Coarse to Fine: A Training-Free Framework for Hierarchical Traceability of Adversarial Attacks in Remote Sensing Systems

    by Zhentong Zhang, Xinde Li, Guoliang Wu, Jianye Yuan, Jinliang Ding, Zhijun Li

    Adversarial attacks present a severe threat to the trustworthiness of remote sensing uncrewed systems. Existing detection methods are mostly limited to binary classification, lacking fine-grained traceability and relying heavily on adversarial example (AE) training. To overcome these challenges, we propose a training-free hierarchical adversarial attack traceability framework leveraging the zero-shot transfer ability of contrastive language-image pretraining (CLIP), eliminating the dependency on AE training. For the first time, we establish a multigranularity attack propagation path analysis system. Specifically, the framework leverages CLIP for fine-grained adversarial attack classification without fine-tuning, constructing a hierarchical traceability system (HTS) from coarse-grained to fine-grained semantic levels. Based on Bayesian inference, we design a hierarchical probability fusion method that improves coarse-grained results through maximum a posteriori (MAP) estimation of fine-grained classifiers, collaboratively optimizing hierarchical probability distributions. To capture frequency-domain characteristics of adversarial attacks, we propose a frequency-aware kernel approximation combining high-frequency-enhanced radial basis function (RBF) kernels with ridge regression, improving sensitivity to subtle perturbations in the reproducing kernel Hilbert space (RKHS). This study establishes a comprehensive traceability system for attack propagation chains, providing an interpretable, training-free paradigm for remote sensing security, significantly enhancing fine-grained detection capabilities of uncrewed systems. Extensive experiments on two public remote sensing datasets, RSSSN7 and DWEFS, and one proprietary dataset demonstrate that our method significantly improves adversarial classification accuracy across two victim models, achieving gains of 17.13%/18.89%/13.44% and 17.91%/19.58%/12.17%, respectively, compared with state-of-the-art (SOTA) training-free baselines.


  • Certainty From Uncertainty: Multigranularity Labeling Inspired by Quantum Collapse for Learning With Noisy Labels in Fault Diagnosis

    by Fir Dunkin, Xinde Li, Zhentong Zhang, Kui Wang, Tianrong Gao, Guoliang Wu, Zhijun Li

    Deep learning has demonstrated exceptional performance in fault diagnosis tasks that rely on large-scale datasets. However, the high cost of annotating such datasets has led to the emergence of various automatic annotation methods. While these methods reduce labeling costs, they inevitably introduce noisy labels, which pose significant challenges to the generalization and accuracy of deep learning-based diagnostic models. Although Learning with Noisy Labels (LNL) methods mitigate the adverse effects of noisy labels through strategies such as sample separation or label correction, many rely heavily on their own prediction results to guide subsequent training, which often introduces confirmation bias, limiting the effectiveness of the trained models. To address this limitation, this article draws inspiration from quantum collapse and proposes a novel LNL strategy named Multigranularity Labeling (MgL). By integrating observed labels, pseudolabels, and collapsed labels, MgL constructs the multigranularity labels, designed to suppress confirmation bias and improve the model's tolerance to noisy labels. Extensive experiments validate the effectiveness and superiority of MgL, particularly on training datasets with high noise intensity, such as those with 90% symmetric noise. This advancement offers promising opportunities for applying datasets with lower annotation costs in real-world scenarios, ultimately contributing to intelligent diagnostic systems.


  • Trust Measurement of Visual Data Based on Multigranularity Belief Fusion for UAV Perception System

    by Heqing Li, Xinde Li, Fir Dunkin, Zhentong Zhang, Chuanfei Hu, Guoliang Wu, Shuzhi Sam Ge

    Unmanned aerial vehicle (UAV) visual perception plays a pivotal role in the realm of intelligent big data applications such as smart transportation, urban planning, and precision agriculture. Ensuring the integrity and reliability of data collected by UAVs is essential to prevent potential misinformation and tampering in critical data acquisition tasks. However, conventional single assessment and decision-making mechanisms have demonstrated limitations, leaving systems vulnerable to security threats in realworld scenarios. In this study, we propose an innovative trust measurement framework based on multi-granularity belief fusion (TM-MGBF), aimed at bolstering the reliability of UAV visual data and mitigating the risks posed by malicious attacks. The integration of multi-granularity trust measurement offers enhanced adaptability and accuracy, offering a promising avenue to address the aforementioned challenges. Specifically, our approach involves devising distinct methodologies for assessing trust across diverse data sources to ascertain their trustworthiness. Furthermore, we introduce an improved fusion strategy, achieving more rational trust measurement by weighting the importance assessment of trust evidence. Experimental results validate the efficacy of the proposed trust model based on multi-granularity belief fusion, showcasing its superior performance in the evaluation of visual perception data and the fortification of UAV perception systems’ security posture.


  • Dual-Branch Sparse Self-Learning With Instance Binding Augmentation for Adversarial Detection in Remote Sensing Images

    by Zhentong Zhang, Xinde Li, Heqing Li, Fir Dunkin, Bing Li, Zhijun Li

    Remote sensing image analysis technology based on neural networks has significantly facilitated human life. However, adversarial attacks can drastically impair the performance of these models, posing substantial economic and security risks. Current adversarial example (AE) detectors primarily focus on studying attacked natural images, while AEs in the remote sensing domain have not received adequate attention. To address this challenge, we propose a novel dual-branch sparse self-learning framework, leveraging instance binding augmentation. The contrastive branch concurrently enhances intra-instance and inter-example feature discrimination, while the masked branch reconstructs perturbation distributions. Furthermore, our method utilizes sparse encoding within depthwise separable convolutions to efficiently transfer parameters, thereby ensuring compatibility with deployment on mobile devices. Extensive experiments demonstrate that our method achieves state-of-the-art performance in detecting both white-box and black-box attacks on remote sensing images. Specifically, our method achieves an average detection accuracy of 95.69%/95.18%, a recall of 91.8%/93.6%, and an F1 score of 93.48%/94.22% on two attacked models across various attack scenarios, outperforming existing methods.


  • ESUAV-NI: Endogenous Security Framework for UAV Perception System Based on Neural Immunity

    by Heqing Li, Xinde Li, Zhentong Zhang, Chuanfei Hu, Fir Dunkin, Shuzhi Sam Ge

    Unmanned aerial vehicles (UAVs) represent an essential component of advanced intelligent equipment that can be used as an aerial perception system by installing various sensors such as vision, hearing, touch, taste, and smell to achieve intelligently integrated perception of environments. However, these perception system with environmental information may be threatened by various internal and external attacks, causing a great challenge to the security of the UAV. The original security system relied on an expert knowledge base to prevent attacks, but the weaknesses of lacking proactivity and flexibility are gradually exposed. The strong resistance and survivability of biological systems can be used to fill this capability gap and provide new ideas for the security of the UAV perception system. Therefore, an endogenous security framework (ESUAV-NI) based on the neural system and immune system is proposed in this article. Through breeding artificial intelligence (AI) vaccines and distributed neural hierarchical control, we achieve the security protection for the UAV perception system. Moreover, we evaluated the AI vaccine breeding approach in the ESUAV-NI by conducting extensive experiments on internal threats and external aerial imagery camouflage data, respectively. The results show that the proposed approach has a superior performance for the UAV perception system.