Xiaopei Zhu

Dr. Xiaopei Zhu


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
31 October 2023 in Applied Intelligence
Verified
Journal Article
Closed access
PDF file
XZXiaopei Zhu
Xiaopei Zhu
ZHZhanhao Hu
Zhanhao Hu
SHSiyuan Huang
Siyuan Huang
JLJianmin Li
Jianmin Li
XHXiaolin Hu
Xiaolin Hu
ZWZheyao Wang
Zheyao Wang

16 October 2023 in Neurocomputing
Verified
Journal Article
Closed access
XZXiaopei Zhu
Xiaopei Zhu
XLXiao Li
Xiao Li
JLJianmin Li
Jianmin Li
ZWZheyao Wang
Zheyao Wang
XHXiaolin Hu
Xiaolin Hu

1 October 2025 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
XZXiaopei Zhu
Xiaopei Zhu
SHSiyuan Huang
Siyuan Huang
ZHZhanhao Hu
Zhanhao Hu
JLJianmin Li
Jianmin Li
JZJun Zhu
Jun Zhu
XHXiaolin Hu
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.

28 October 2024
Verified
Conference Paper
Open access
XZXiaopei Zhu
Xiaopei Zhu
PXPeiyang Xu
Peiyang Xu
GZGuanning Zeng
Guanning Zeng
YDYinpeng Dong
Yinpeng Dong
XHXiaolin Hu
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.


1 April 2026 in IEEE/CAA Journal of Automatica Sinica
Verified
Journal Article
Closed access
YLYuqiu Liu
Yuqiu Liu
HYHuanqian Yan
Huanqian Yan
XZXiaopei Zhu
Xiaopei Zhu
XHXiaolin Hu
Xiaolin Hu
LTLiang Tang
Liang Tang
CLChen Lv
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.