XZXiaopei Zhu

Xiaopei Zhu

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Xiaopei Zhu has a total of 19 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.

  • Physical Adversarial Examples for Person Detectors in Thermal Images Based on 3D Modeling

    by Xiaopei Zhu, Siyuan Huang, Zhanhao Hu, Jianmin Li, Jun Zhu, Xiaolin Hu

    Thermal Infrared detection is widely used in autonomous driving, medical AI, etc., but its security has only attracted attention recently. We propose infrared adversarial clothing designed to evade thermal person detectors in real-world scenarios. The design of the adversarial clothing is based on 3D modeling, which makes it easier to simulate multiangle scenes near the real world compared to 2D modeling. We optimized the black patch layout pattern of 3D clothing based on the adversarial example technique and made physical adversarial clothing using the aerogel. The idea is to paste a set of square aerogel patches, which display black squares in thermal images, in the inner side of clothing at specific locations with specific orientations. To enhance realism, we propose a method to build infrared 3D models with real infrared photos and develop texture maps for 3D models to simulate varied infrared characteristics over time and location. In physical attacks, we achieved an attack success rate of 80.11% indoors and 76.85% outdoors against YOLOv9. In contrast, randomly placed patches yielded much lower success rates (26.53% indoors and 23.03% outdoors). The adversarial clothing also showed good transferability to unknown detectors with an ensemble attack method, demonstrating the effectiveness of our approach.


  • Open Access

    Natural Language Induced Adversarial Images

    by Xiaopei Zhu, Peiyang Xu, Guanning Zeng, Yinpeng Dong, Xiaolin Hu

    Research of adversarial attacks is important for AI security because it shows the vulnerability of deep learning models and helps to build more robust models. Adversarial attacks on images are most widely studied, which include noise-based attacks, image editing-based attacks, and latent space-based attacks. However, the adversarial examples crafted by these methods often lack sufficient semantic information, making it challenging for humans to understand the failure modes of deep learning models under natural conditions. To address this limitation, we propose a natural language induced adversarial image attack method. The core idea is to leverage a text-to-image model to generate adversarial images given input prompts, which are maliciously constructed to lead to misclassification for a target model. To adopt commercial text-to-image models for synthesizing more natural adversarial images, we propose an adaptive genetic algorithm (GA) for optimizing discrete adversarial prompts without requiring gradients and an adaptive word space reduction method for improving query efficiency. We further used CLIP to maintain the semantic consistency of the generated images. In our experiments, we found that some high-frequency semantic information such as ''foggy'', ''humid'', ''stretching'', etc. can easily cause classifier errors. This adversarial semantic information exists not only in generated images but also in photos captured in the real world. We also found that some adversarial semantic information can be transferred to unknown classification tasks. Furthermore, our attack method can transfer to different text-to-image models (e.g., Midjourney, DALL·E 3, etc.) and image classifiers. Our code is available at:https://github.com/zxp555/Natural-Language-Induced-Adversarial-Images.


  • Hiding from infrared detectors in real world with adversarial clothes

    by Xiaopei Zhu, Zhanhao Hu, Siyuan Huang, Jianmin Li, Xiaolin Hu, Zheyao Wang


  • Hiding from thermal imaging pedestrian detectors in the physical world

    by Xiaopei Zhu, Xiao Li, Jianmin Li, Zheyao Wang, Xiaolin Hu