Qiqi Bao

Qiqi Bao

Auto-generated profile, based on publicly available information

Qiqi Bao

School of Artificial Intelligence and Information Engineering, Zhejiang University of Science and Technology, Hangzhou, China

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
18 February 2026 in Knowledge-Based Systems
Verified
Journal Article
Closed access
Shengying YangShengying Yang
Shengying Yang
XRXiangyu Ren
Xiangyu Ren
BZBingxin Zha
Bingxin Zha
QBQiqi Bao
Qiqi Bao
BFBoyang Feng
Boyang Feng
ZXZhiwang Xu
Zhiwang Xu

21 August 2025 in IEEE Transactions on Dependable and Secure Computing
Verified
Journal Article
Closed access
YQYaguan Qian
Yaguan Qian
QYQinqin Yu
Qinqin Yu
QBQiqi Bao
Qiqi Bao
SJShouling Ji
Shouling Ji
WWWei Wang
Wei Wang
ZLZhen Lei
Zhen Lei
Vision-language pretraining (VLP) models have demonstrated outstanding performance in image-text understanding tasks but remain highly susceptible to transferable adversarial attacks. While ensemble-based guided attacks improve adversarial transferability by increasing the diversity of image-text pairs, they primarily rely on spatial-domain data augmentation, which can lead to model overfitting to image details and limit the generalization capability of attacks. To address this limitation, this study proposes a frequency-domain adjustment-based adversarial attack method that modifies specific frequency components of input images to reduce detail interference and enhance the stability of adversarial examples. Additionally, a fine-grained feature extraction technique is introduced to optimize image-text alignment, further improving the transferability of cross-modal attacks. Experimental results demonstrate that the proposed method achieves superior attack transferability and generalization performance across two major VLP architectures, fusion models and alignment models, as well as multiple tasks on the Flickr30 K and MSCOCO datasets.

28 January 2026 in IEEE Transactions on Image Processing
Verified
Journal Article
Closed access
YQYaguan Qian
Yaguan Qian
YKYaxin Kong
Yaxin Kong
QBQiqi Bao
Qiqi Bao
ZGZhaoquan Gu
Zhaoquan Gu
BWBin Wang
Bin Wang
ZLZhen Lei
Zhen Lei
Vision–Language Pretrained (VLP) models exhibit strong multimodal understanding and reasoning capabilities, finding wide application in tasks such as image–text retrieval and visual grounding. However, they remain highly vulnerable to adversarial attacks, posing serious reliability concerns in safety-critical scenarios. We observe that existing adversarial examples optimization methods typically rely on individual features from the other modality as guidance, causing the crafted adversarial examples to overfit that modality’s learning preferences and thus limiting their transferability. In order to further enhance the transferability of adversarial examples, we propose a novel adversarial attack framework, I&CA (Individual & Common feature Attack), which simultaneously considers individual features within each modality and common features cross-modal interactions. Concretely, I&CA first drives divergence among individual features within each modality to disrupt single-modality learning, and then suppresses the expression of common features during cross-modal interactions, thereby undermining the robustness of the fusion mechanism. In addition, to prevent adversarial perturbations from overfitting to the learning bias of the other modality, which may distort the representation of common features, we simultaneously introduce augmentation strategies to both modalities. Across various experimental settings and widely recognized multimodal benchmarks, the I&CA framework achieves an average transferability improvement of 6.15% over the state-of-the-art DRA method, delivering significant performance gains in both cross-model and cross-task attack scenarios.

26 December 2025 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Closed access
YQYaguan Qian
Yaguan Qian
XZXucheng Zhu
Xucheng Zhu
QBQiqi Bao
Qiqi Bao
FYFei Yu
Fei Yu
SJShouling Ji
Shouling Ji
ZLZhen Lei
Zhen Lei
With the rapid development of Large Language Models (LLMs), an increasing number of Large Visual-Language Models (LVLMs) have achieved unprecedented performance in response generation. Recent work shows that LVLMs are vulnerable to adversarial attacks. However, many existing methods tend to overfit to the source model by overemphasizing specific features, which compromises their transferability. Other approaches suffer from reduced attack effectiveness due to insufficient differentiation between features. In this paper, we propose a novel transfer-based black-box untargeted attack—Shared Adversarial Feature (SAF) dynamic attack. By exploring the feature extraction patterns of LVLMs, we identify the features shared among various models that are most susceptible to adversarial attacks and disrupt them. Moreover, due to the powerful attention mechanisms of LVLMs, they are still able to extract similar semantics from perturbed images, even when primary features are disrupted. We design a dynamic update strategy to address this challenge. Finally, from the perspective of SAF, we conduct an in-depth analysis of vulnerabilities in the vision encoder and projector within LVLMs and find that attacking the projector exhibits stronger transferability across heterogeneous model architectures. Extensive experiments show that our method exhibits superior attack performance compared to existing methods across different models, datasets, and tasks. The code will be publicly available after publication.

10 December 2025 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Open access
YQYaguan Qian
Yaguan Qian
ZCZhihao Chen
Zhihao Chen
QBQiqi Bao
Qiqi Bao
CZChang Zong
Chang Zong
FYFei Yu
Fei Yu
ZLZhen Lei
Zhen Lei
Current adversarial attacks pose a serious threat to the robustness of visual-language models (VLMs), including vision-language pre-trained models (VLPMs) and multimodal large language models (MLLMs). Traditional adversarial attacks are example-specific and rely on specific datasets. This practice suffers from low transferability and additional computation cost, while universal adversarial perturbations (UAPs) offer example-agnostic solutions by generalizing across inputs. However, current UAP methods mainly target VLPMs, demonstrating limited transferability and effectiveness in MLLMs. To bridge this gap, we propose the Recursive Perturbation Attack (RPA), a novel black-box UAP method for both VLPMs and MLLMs. RPA employs a recursive perturbations strategy, utilizing token filtering and polynomial sampling methods to generate perturbations, thereby achieving incremental disruption and enhancing the transferability of the attack. To further enhance the effectiveness of the attack, RPA integrates a three-tier modality decoupling strategy, disentangling intra-modal, cross-modal, and fusion-modal features to effectively disrupt feature alignment and interactions. Extensive experiments validate that RPA achieves superior attack performance compared to existing UAP approaches. This work highlights new security concerns in multimodal AI systems and provides insights into the design of more robust models. Code is available at https://github.com/chilljudaoren/RPAttack.

15 September 2026 in ACM Transactions on Multimedia Computing, Communications, and Applications
Verified
Journal Article
Open access
XZXinyi Zhang
Xinyi Zhang
QBQiqi Bao
Qiqi Bao
Wenming YangWenming Yang
Wenming Yang
QLQingmin Liao
Qingmin Liao
JXJing-Hao Xue
Jing-Hao Xue
Transformers have become dominant in 3D Human Pose Estimation (HPE). However, existing Transformer-based 3D HPE backbones often encounter a trade-off between accuracy and computational efficiency. To resolve the above dilemma, in this work we leverage recent advances in state space models and utilize Mamba for high-quality and efficient long-range modeling. Nonetheless, Mamba still faces challenges in precisely exploiting local dependencies between joints. To address these issues, we propose a novel attention-free integrated spatiotemporal architecture named I ntegrated Ma mba-Hyper GC N (Pose Magic++). This architecture introduces local enhancement with HyperGCN by capturing relationships between neighboring joints and their synergies, producing new representations to complement Mamba's outputs. By adaptively fusing representations from Mamba and HyperGCN, Pose Magic++ demonstrates superior capability in learning the underlying 3D structure. To meet the requirements of real-time inference, we also provide a fully causal version. Extensive experiments show that Pose Magic++ achieves new state-of-the-art (SOTA) results ( \(\downarrow 1.6mm\) ) while saving \(74.1\%\) FLOPs. Notably, it significantly improves the estimation accuracy of peripheral joints without incurring extra computational cost. In addition, Pose Magic++ exhibits optimal motion consistency and strong ability to generalize to unseen sequence lengths.