Chengyin Hu

Chengyin Hu

Auto-generated profile, based on publicly available information

Chengyin Hu

China University of Petroleum‐Beijing at Karamay Karamay Xinjiang China

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
18 January 2024 in IET Computer Vision
Verified
Journal Article
Open access
CHChengyin Hu
Chengyin Hu
WSWeiwen Shi
Weiwen Shi
LTLing Tian
Ling Tian
WLWen Li
Wen Li
Recent studies have demonstrated that finely tuned deep neural networks (DNNs) are susceptible to adversarial attacks. Conventional physical attacks employ stickers as perturbations, achieving robust adversarial effects but compromising stealthiness. Recent innovations utilise light beams, such as lasers and projectors, for perturbation generation, allowing for stealthy physical attacks at the expense of robustness. In pursuit of implementing both stealthy and robust physical attacks, the authors present an adversarial catoptric light (AdvCL). This method leverages the natural phenomenon of catoptric light to generate perturbations that are both natural and stealthy. AdvCL first formalises the physical parameters of catoptric light and then optimises these parameters using a genetic algorithm to derive the most adversarial perturbation. Finally, the perturbations are deployed in the physical scene to execute stealthy and robust attacks. The proposed method is evaluated across three dimensions: effectiveness, stealthiness, and robustness. Quantitative results obtained in simulated environments demonstrate the efficacy of the proposed method, achieving an attack success rate of 83.5%, surpassing the baseline. The authors utilise common catoptric light as a perturbation to enhance the method's stealthiness, rendering physical samples more natural in appearance. Robustness is affirmed by successfully attacking advanced DNNs with a success rate exceeding 80% in all cases. Additionally, the authors discuss defence strategies against AdvCL and introduce some light‐based physical attacks.


9 November 2026
Verified
Conference Paper
Open access
CHChengyin Hu
Chengyin Hu
XSXuemeng Sun
Xuemeng Sun
JHJiaju Han
Jiaju Han
QZQike Zhang
Qike Zhang
XCXiang Chen
Xiang Chen
JLJiahuan Long
Jiahuan Long

1 January 2026 in IET Computer Vision
Verified
Journal Article
Open access
KTKalibinuer Tiliwalidi
Kalibinuer Tiliwalidi
FLFalei Liu
Falei Liu
WLWenjun Li
Wenjun Li
CHChengyin Hu
Chengyin Hu
XKXu Kang
Xu Kang
ZRZhihong Rao
Zhihong Rao
Infrared imaging technology holds a prominent position across various applications, particularly with the burgeoning significance of infrared object detection technology. Although prior research has explored physical attacks on infrared object detectors, the practical implementation of these techniques remains intricate. For example, certain methodologies involve the deployment of specialised equipment such as bulb boards or infrared QR suits to execute attacks, necessitating costly optimisation and cumbersome deployment processes. Alternatively, other strategies employ irregular aerogel as physical perturbations for infrared attacks, albeit with associated optimisation expenses and perceptibility issues. In this study, we introduce a novel infrared physical attack termed ‘adversarial infrared geometry’ (AdvIG), which enables efficient black‐box query attacks by modelling diverse geometric shapes such as lines, triangles and ellipses and optimising their physical parameters using particle swarm optimisation (PSO). We conduct extensive experiments to assess the effectiveness, stealthiness and robustness of AdvIG. In digital attack experiments, line, triangle and ellipse patterns achieve success rates of 93.1%, 86.8% and 100.0%, respectively, with average query times of 71.7, 113.1 and 2.6, respectively, thereby confirming the efficiency of AdvIG. Physical attack experiments are performed to evaluate the success rate of AdvIG at various distances. On average, the success rates for lines, triangles and ellipses are 61.1%, 61.2% and 96.2%, respectively. We further conduct comprehensive experiments to analyse AdvIG, including ablation experiments, transfer attack experiments and assessments of adversarial defence mechanisms. Given the superior performance of our method as a simple and efficient black‐box adversarial attack in both digital and physical environments, we advocate broader attention to AdvIG.

15 June 2026
Verified
Conference Paper
Open access
CHChengyin Hu
Chengyin Hu
YCYijun Chen
Yijun Chen
TLTianle Liang
Tianle Liang
YWYiwei Wei
Yiwei Wei
ALAng Li
Ang Li
XSXuelian Shi
Xuelian Shi
Despite strong performance on open-source large vision-language models (LVLMs), transfer-based targeted adversarial attacks often fail against closed-source commercial LVLMs. Existing methods typically rely on static perturbation allocation and uniformly weighted surrogate ensembles, limiting their ability to capture model-agnostic semantic vulnerabilities essential for cross-model transferability. Consequently, perturbations are frequently allocated to semantically irrelevant regions, reducing effectiveness under realistic black-box settings. To address this limitation, we propose the Gated Multi-signal Adaptive Ensemble (GMAE) framework, a novel transfer-based targeted attack that formulates adversarial generation as a joint optimization over a gated perturbation field and an adaptive ensemble objective. A learnable spatial gating mask dynamically reallocates perturbation budgets toward semantically vulnerable regions, while surrogate models are adaptively reweighted according to optimization difficulty and historical consistency, encouraging alignment on shared semantic weaknesses across heterogeneous architectures. To further enhance robustness, GMAE performs global semantic alignment in a symbolic discrete space, reducing the influence of non-essential feature variations and improving cross-model generalization. In addition, we introduce a local attention-guided multi-scale consistency mechanism that transfers fine-grained target textures into attention-identified sensitive regions, ensuring both visual imperceptibility and semantic coherence at feature and concept levels. Extensive experiments demonstrate that GMAE achieves strong transferability to commercial LVLMs, and reasoning-oriented models. Notably, GMAE achieves an attack success rate of 82.90% on GPT-4o, outperforming the strongest baseline by 7.8%, establishing a new state of the art for targeted transfer attacks on large-scale black-box LVLMs.

18 July 2025
Verified
Conference Paper
Open access
WLWenjun Li
Wenjun Li
CHChengyin Hu
Chengyin Hu
KLKaifei Li
Kaifei Li
JDJiani Duan
Jiani Duan
RZRongqi Zhang
Rongqi Zhang