HYHuanqian Yan

Huanqian Yan

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Huanqian Yan has a total of 67 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Crafting Physical Adversarial Examples by Combining Differentiable and Physically Based Renders

    by Yuqiu Liu, Huanqian Yan, Xiaopei Zhu, Xiaolin Hu, Liang Tang, Hang Su, Chen Lv

    Recently, we have witnessed progress in hiding road vehicles against object detectors through adversarial camouflage in the digital world. The extension of this technique to the physical world is crucial for testing the robustness of autonomous driving systems. However, existing methods do not show good performances when applied to the physical world. This is partly due to insufficient photorealism in training examples, and lack of proper physical realization methods for camouflage. To generate a robust adversarial camouflage suitable for real vehicles, we propose a novel method called physical adversarial vehicle camouflage (PAV-Camou). We propose to adjust the mapping from the coordinates in the 2D map to those of corresponding 3D model. This process is critical for mitigating texture distortion and ensuring the camouflage's effectiveness when applied in the real world. Then we combine two renderers with different characteristics to obtain adversarial examples that are photorealistic and closely mimic real-world lighting and texture properties. The method ensures that the generated textures remain effective under diverse environmental conditions. Our adversarial camouflage can be optimized and printed in the form of 2D patterns, allowing for direct application on real vehicles. Extensive experiments demonstrated that our proposed method achieved good performance in both the digital world and the physical world.

  • Open Access

    MSF-SKNet: Multispectral Man-made Material Object Detection with Selective Kernel Attention

    by Qiong Ran, Zihan Xu, Hongqi Zhang, Jinlin Chen, Huanqian Yan, He Sun

    The detection of man-made materials in complex environments is critical for applications ranging from public safety to disaster relief. However, these materials often exhibit high textural and chromatic similarity to natural backgrounds, rendering traditional visible-light detection methods ineffective due to severe visual ambiguity. While multispectral imaging provides discriminative spectral signatures, current research is constrained by the scarcity of specialized benchmarks and the limitation of standard Convolutional Neural Networks (CNNs) in adaptively extracting features from high-dimensional spectral data. To address these challenges, this paper presents two systematic contributions. First, we construct and release the Multispectral Man-made Material Object Detection (MMMOD) dataset. As the first benchmark dedicated to man-made material objects, it encompasses six typical material categories across diverse seasonal and spatial scenarios, bridging a critical data gap in the field. Second, we propose the Multispectral Feature-Selection Network with SKAttention (MSF-SKNet). By integrating a Selective Kernel Attention mechanism, our method enables the dynamic adjustment of receptive field sizes and the adaptive recalibration of channel weights. This design effectively resolves the structural mismatch between fixed convolution kernels and the varying scales of multispectral objects. It significantly outperforms mainstream state-of-the-art detectors, establishing a new benchmark for robust multispectral object detection.

  • Open Access

    Small-Vehicle Change Detection in UAV Imagery via Physics-Aware Spatiotemporal Cues and Reproducible Evaluation

    by Qiong Ran, Pengfei Bian, Luyang Cai, Jinlin Chen, Huanqian Yan, He Sun

    Vehicle detection holds significant research value and practical application potential. However, existing vehicle detection algorithms struggle to meet the demands for fast, accurate detection and tracking of weak and small targets in unmanned aerial vehicle (UAV) remote sensing imagery. In this work, weak targets refer to vehicle targets with small spatial extent, low contrast with the background, and subtle temporal changes, which are difficult to detect reliably in UAV imagery. To address this issue, this paper proposes a bi-temporal change detection method based on spatiotemporal features. Specifically, the proposed method involves processing the data captured by UAVs, applying feature point matching for image alignment, and performing change detection on bitemporal data to achieve more precise recognition of vehicle targets. The results demonstrate that the proposed algorithm exhibits more competitive detection performance compared to traditional unsupervised methods such as change vector analysis (CVA), differential component analysis (DPCA), iteratively weighted multivariate extinction detection (IRMAD), and multivariate detection (MAD). Compared to traditional methods, our proposed method achieves superior performance in detecting small and weak targets, particularly excelling in identifying weak targets while reducing the occurrence of false positives.

  • Top Cited Papers

    Boosting Jailbreak Transferability for Large Language Models

    by Jian Zheng, Hanqing Liu, Lifeng Zhou, Huanqian Yan, Peilin Liu


  • HF-MCD: A Heterogeneous Fusion Framework for Multimodal Change Detection

    by Luyang Cai, He Sun, Xu Sun, Huanqian Yan, Lianru Gao

    Multimodal change detection (MCD) aims to detect changed areas between the bi-temporal multimodal images such as the RGB, panchromatic (PAN), multispectral (MS), and synthetic aperture radar (SAR) images, which has attracted attention in recent years. However, existing deep learning-based methods for MCD tasks still face several heterogeneity factors, the first one is the spatial resolution differences in multimodal data, which leads to the semantic gap between multimodal features. To solve this problem, we propose the heterogeneous collaborative fusion (HCF) module to integrate the multimodal features with spatial gaps. The other one is the consistency and dissimilarity between multimodal data, which lead to unequal detection contributions. To address this dilemma, we propose the heterogeneous adaptive fusion (HAF) module to fuse multimodal decision-making jointly. In this study, we proposed a heterogeneous fusion network for MCD (HF-MCD) with the HCF and the HAF module. We validate the proposed method on four public available MCD datasets. Extensive experimental results have demonstrated the superior performance of HF-MCD over the state-of-the-art methods.


  • Open Access

    Distillation-Enhanced Physical Adversarial Attacks

    by Wei Liu, Yonglin Wu, Chaoqun Li, Zhuodong Liu, Huanqian Yan

    The study of physical adversarial patches is crucial for identifying vulnerabilities in AI-based recognition systems and developing more robust deep learning models. While recent research has focused on improving patch stealthiness for greater practical applicability, achieving an effective balance between stealth and attack performance remains a significant challenge. To address this issue, we propose a novel physical adversarial attack method that leverages knowledge distillation. Specifically, we first define a stealthy color space tailored to the target environment to ensure smooth blending. Then, we optimize an adversarial patch in an unconstrained color space, which serves as the 'teacher' patch. Finally, we use an adversarial knowledge distillation module to transfer the teacher patch's knowledge to the 'student' patch, guiding the optimization of the stealthy patch. Experimental results show that our approach improves attack performance by 20%, while maintaining stealth, highlighting its practical value.


  • Open Access

    Global Challenge for Safe and Secure LLMs Track 1

    by Xiaojun Jia, Yihao Huang, Yang Liu, Peng Yan Tan, Weng Kuan Yau, Mun-Thye Mak, Xin Ming Sim, Wee Siong Ng, See Kiong Ng, Hanqing Liu, et al.

    This paper introduces the Global Challenge for Safe and Secure Large Language Models (LLMs), a pioneering initiative organized by AI Singapore (AISG) and the CyberSG R&D Programme Office (CRPO) to foster the development of advanced defense mechanisms against automated jailbreaking attacks. With the increasing integration of LLMs in critical sectors such as healthcare, finance, and public administration, ensuring these models are resilient to adversarial attacks is vital for preventing misuse and upholding ethical standards. This competition focused on two distinct tracks designed to evaluate and enhance the robustness of LLM security frameworks. Track 1 tasked participants with developing automated methods to probe LLM vulnerabilities by eliciting undesirable responses, effectively testing the limits of existing safety protocols within LLMs. Participants were challenged to devise techniques that could bypass content safeguards across a diverse array of scenarios, from offensive language to misinformation and illegal activities. Through this process, Track 1 aimed to deepen the understanding of LLM vulnerabilities and provide insights for creating more resilient models.

  • Empowering Object Detection: Unleashing the Potential of Decoupled and Interactive Distillation

    by Fulan Qian, Jiacheng Hong, Huanqian Yan, Hai Chen, Chonghao Zhang, Hang Su, Shu Zhao

    Deploying state-of-the-art object detectors on resource-limited devices presents significant challenges. Knowledge distillation is an efficient and streamlined lightweight technique to improve the accuracy of compact detectors. However, its effectiveness is limited by the redundancy of different types of semantics on the feature map and the closure of same level’s feature distillation. To alleviate this problem, we propose Decoupled and Interactive Distillation, an effective and versatile method to improve knowledge distillation in some complex object detection tasks. The method has two key components. A knowledge decoupled module captures category awareness and localization awareness features. A multi-level feature interaction distillation can aggregate feature distillations from shallow to deep levels, facilitating the collaboration between feature transfers at different levels. The relevant experiments in traffic-related, 3D, rotated object detection have verified the effectiveness of the proposed method, particularly in challenging scenes.


  • ANF: Crafting Transferable Adversarial Point Clouds via Adversarial Noise Factorization

    by Hai Chen, Shu Zhao, Xiao Yang, Huanqian Yan, Yuan He, Hui Xue, Fulan Qian, Hang Su

    Transfer-based adversarial attacks involve generating adversarial point clouds in surrogate models and transferring them to other models to assess 3D model robustness. However, current methods rely too much on surrogate model parameters, limiting transferability. In this work, we use Shapley value to identify positive and negative features, guiding optimization of adversarial noise in feature space. To effectively mislead the 3D classifier, we factorize the adversarial noise into positive and negative noise, with the former keeping the features of the adversarial point cloud close to the negative features, and the latter and the adversarial noise moving it away from the positive features. Finally, a novel adversarial point cloud attack method with Adversarial Noise Factorization is proposed, which is abbreviated as ANF. ANF simultaneously optimizes the adversarial noise and its positive and negative noise in the feature space, only relying on partial network parameters, which significantly reduces the reliance on the surrogate model and improves the transferability of the adversarial point cloud. Experiments on well-recognized benchmark datasets show that the transferability of adversarial point clouds generated by ANF could be improved by more than 26.7$\%$ on average over state-of-the-art transfer-based adversarial attack methods.


  • Efficient Adversarial Attack Strategy Against 3D Object Detection in Autonomous Driving Systems

    by Hai Chen, Huanqian Yan, Xiao Yang, Hang Su, Shu Zhao, Fulan Qian

    The reliability and robustness of 3D object detection play an instrumental role in the practical deployment of autonomous driving systems. Despite previous research indicating that adversarial examples can negatively affect 3D object detection models, leading to misinterpretations of the environment, these models still maintain the capability to detect the majority of objects within adversarially manipulated point clouds. To further probe into the adversarial robustness of these models, we propose an effective adversarial attack method named IoU-S attack in this paper. We meticulously formulate the adversarial loss to adversely affect the decision-making behavior (such as localization, etc.) of 3D object detection, thereby compromising its ability to accurately interpret the environment. Owing to the significant relevance of this adversarial loss to 3D object detection tasks, we have integrated the IoU-S attack into three attack paradigms: point cloud perturbation, detachment, and attachment. Comprehensive experiments on the widely accepted nuScenes dataset illustrate that the IoU-S attack outperforms existing attack methods in both white-box and black-box scenarios (https://github.com/haichen-ber/IoU-S-Attack). It reinforces its potential to serve as a valuable method in understanding and enhancing the robustness of 3D object detection models against adversarial attacks.