Author name cluster

HaiJing Guo

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

4 papers

1 author row

NeurIPS Conference 2025 Conference Paper

Boosting Adversarial Transferability with Spatial Adversarial Alignment

Zhaoyu Chen
HaiJing Guo
Kaixun Jiang
Jiyuan Fu
Xinyu Zhou
Dingkang Yang
Hao Tang
Bo Li

Deep neural networks are vulnerable to adversarial examples that exhibit transferability across various models. Numerous approaches are proposed to enhance the transferability of adversarial examples, including advanced optimization, data augmentation, and model modifications. However, these methods still show limited transferability, partiovovocularly in cross-architecture scenarios, such as from CNN to ViT. To achieve high transferability, we propose a technique termed Spatial Adversarial Alignment (SAA), which employs an alignment loss and leverages a witness model to fine-tune the surrogate model. Specifically, SAA consists of two key parts: spatial-aware alignment and adversarial-aware alignment. First, we minimize the divergences of features between the two models in both global and local regions, facilitating spatial alignment. Second, we introduce a self-adversarial strategy that leverages adversarial examples to impose further constraints, aligning features from an adversarial perspective. Through this alignment, the surrogate model is trained to concentrate on the common features extracted by the witness model. This facilitates adversarial attacks on these shared features, thereby yielding perturbations that exhibit enhanced transferability. Extensive experiments on various architectures on ImageNet show that aligned surrogate models based on SAA can provide higher transferable adversarial examples, especially in cross-architecture attacks.

PDF Details

NeurIPS Conference 2025 Conference Paper

Dynamic Semantic-Aware Correlation Modeling for UAV Tracking

Xinyu Zhou
Tongxin Pan
Lingyi Hong
Pinxue Guo
HaiJing Guo
Zhaoyu Chen
Kaixun Jiang
Wenqiang Zhang

UAV tracking can be widely applied in scenarios such as disaster rescue, environmental monitoring, and logistics transportation. However, existing UAV tracking methods predominantly emphasize speed and lack exploration in semantic awareness, which hinders the search region from extracting accurate localization information from the template. The limitation results in suboptimal performance under typical UAV tracking challenges such as camera motion, fast motion, and low resolution, etc. To address this issue, we propose a dynamic semantic aware correlation modeling tracking framework. The core of our framework is a Dynamic Semantic Relevance Generator, which, in combination with the correlation map from the Transformer, explore semantic relevance. The approach enhances the search region's ability to extract important information from the template, improving accuracy and robustness under the aforementioned challenges. Additionally, to enhance the tracking speed, we design a pruning method for the proposed framework. Therefore, we present multiple model variants that achieve trade-offs between speed and accuracy, enabling flexible deployment according to the available computational resources. Experimental results validate the effectiveness of our method, achieving competitive performance on multiple UAV tracking datasets.

PDF Details

NeurIPS Conference 2025 Conference Paper

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment

Kaixun Jiang
Zhaoyu Chen
HaiJing Guo
Jinglun Li
Jiyuan Fu
Pinxue Guo
Hao Tang
Bo Li

Preference alignment in diffusion models has primarily focused on benign human preferences (e. g. , aesthetic). In this paper, we propose a novel perspective: framing unrestricted adversarial example generation as a problem of aligning with adversary preferences. Unlike benign alignment, adversarial alignment involves two inherently conflicting preferences: visual consistency and attack effectiveness, which often lead to unstable optimization and reward hacking (e. g. , reducing visual quality to improve attack success). To address this, we propose APA (Adversary Preferences Alignment), a two-stage framework that decouples conflicting preferences and optimizes each with differentiable rewards. In the first stage, APA fine-tunes LoRA to improve visual consistency using rule-based similarity reward. In the second stage, APA updates either the image latent or prompt embedding based on feedback from a substitute classifier, guided by trajectory-level and step-wise rewards. To enhance black-box transferability, we further incorporate a diffusion augmentation strategy. Experiments demonstrate that APA achieves significantly better attack transferability while maintaining high visual consistency, inspiring further research to approach adversarial attacks from an alignment perspective.

PDF Details

EAAI Journal 2025 Journal Article

Multiscale constitutive modeling of anisotropic plasticity: Coupling the visco-plastic self-consistent model with the recurrent neural network and its implementation in finite element analysis

Ziwei Zhou
Liang Cheng
Huaidong Song
HaiJing Guo
Ruolin Li
Lingyan Sun
Bin Tang

The anisotropic and nonlinear strain-path-dependent nature of metal plasticity poses a major challenge for accurate constitutive modeling in finite element (FE) analysis. Traditional macroscale models are easily implemented but lack accuracy, while crystal plasticity (CP) models offer high fidelity at the cost of computational efficiency. To bridge this gap, we propose a deep neural network smart constitutive (DNNSC) framework that combines the visco-plastic self-consistent (VPSC) model with a gated recurrent unit (GRU) network. A VPSC model calibrated on pure aluminum generated 14, 000 strain-paths for training GRU-based network. The optimized model has a prediction accuracy of up to 96 % on unknown strain-paths. Subsequently, the DNNSC model was implemented into the FE analysis through Fortran programming, and a benchmark simulation for thin sheet stamping was successfully performed. The simulation results demonstrated that the DNNSC model significantly improved prediction performance compared to conventional macroscale constitutive models. Especially, the ear height and plate thickness were accurately predicted with an accuracy of 91. 85 % and 95. 84 %, compared to only 68. 85 % and 86. 59 % achieved by the Yld model. Meanwhile, the simulation time was reduced to approximately one-tenth that of the fully coupled CP model, because the latter required calculating and homogenizing the mechanical responses of hundreds of grains at each integration point during the simulation. The DNNSC framework bridges the gap between CP models and FE simulations of plastic forming and breaks down the barrier between modeling and practical application. Furthermore, this framework can be extended to other materials by re-calibrating VPSC parameters and fine-tuning DNN parameters.

Details DOI