Haiqi Zhang
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Haiqi Zhang has a total of 15 co-authors. Here are the top co-authors by number of shared publications:
- Hao Tang
Centre for Smart Health, The Hong Kong Polytechnic University, Hong Kong, SAR, China
3 shared publications - Zechao Li
Nanjing University of Science and Technology
3 shared publications - Yanpeng Sun
NExT++ Laboratory, School of Computing, National University of Singapore, Queenstown, Singapore
2 shared publications Beixian Zhang
Guangxi Key Lab of Multi-source Information Mining and Security, Guangxi Normal University, Guilin, China
1 shared publication- Guangquan Lu
Key Lab of Education Blockchain and Intelligent Technology, Ministry of Education, Guangxi Normal University, Guilin, China
1 shared publication - Hao Zheng
Nanjing Xiaozhuang University
1 shared publication
Latest Publications
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (5) , 11375-11392
Beyond Single-Pair Attacks: Disrupting Vision-Language Pre-Training Models With Dual-Semantic Frequency Stealth
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (5) , 11375-11392
Beyond Single-Pair Attacks: Disrupting Vision-Language Pre-Training Models With Dual-Semantic Frequency Stealth
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 15850-15864
A Memetic Search for Multi-Depot Cumulative Capacitated Vehicle Routing Problem
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Automation Science and Engineering
- Vol. 23, 15850-15864
A Memetic Search for Multi-Depot Cumulative Capacitated Vehicle Routing Problem
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (2) , 2198-2214
Gradient Pruning Interactive Attack for Vision-Language Pre-Training Models
Vision-Language Pre-training (VLP) models exhibit pronounced vulnerability to multimodal adversarial examples, necessitating rigorous robustness research, particularly for transferable attacks in black-box scenarios. Current research predominantly enhances attack transferability across VLP models by diversifying image and text inputs. However, during adversarial example generation, these methods often prioritize amplifying inter-modal semantic discrepancies (i.e., modality-discrepancy features) while overlooking model-specific semantic features critical to transferable attacks. To address this limitation, we pro pose a transferable Gradient Pruning Interactive Attack (GPI Attack), which integrates gradient-pruned image perturbations with semantic-oriented text perturbations through modality interaction. For image attacks, extreme backpropagated gradients may cause adversarial examples to highlight certain model specific features, leading to poor transferability. To suppress this feature, the textual modality guides the pruning of extreme gradients within intermediate VLP blocks, and these pruned gradients are subsequently employed to direct the generation of adversarial images. For text attacks, we consolidate the perturbation process solely at the embedding level, which reduces semantic discrepancies across hierarchical structures and significantly enhances the generalizability of adversarial texts. Experimental results demonstrate the effectiveness of GPI-Attack in image text retrieval tasks on multimodal datasets such as Flickr30K and MSCOCO. Additionally, the proposed gradient pruning technique is plug-and-play, showing performance improvements even when applied to baseline methods, indicating its potential as a valuable enhancement for attack performance.
- 24 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Dependable and Secure Computing
- Vol. 23 (2) , 2198-2214
Gradient Pruning Interactive Attack for Vision-Language Pre-Training Models
Vision-Language Pre-training (VLP) models exhibit pronounced vulnerability to multimodal adversarial examples, necessitating rigorous robustness research, particularly for transferable attacks in black-box scenarios. Current research predominantly enhances attack transferability across VLP models by diversifying image and text inputs. However, during adversarial example generation, these methods often prioritize amplifying inter-modal semantic discrepancies (i.e., modality-discrepancy features) while overlooking model-specific semantic features critical to transferable attacks. To address this limitation, we pro pose a transferable Gradient Pruning Interactive Attack (GPI Attack), which integrates gradient-pruned image perturbations with semantic-oriented text perturbations through modality interaction. For image attacks, extreme backpropagated gradients may cause adversarial examples to highlight certain model specific features, leading to poor transferability. To suppress this feature, the textual modality guides the pruning of extreme gradients within intermediate VLP blocks, and these pruned gradients are subsequently employed to direct the generation of adversarial images. For text attacks, we consolidate the perturbation process solely at the embedding level, which reduces semantic discrepancies across hierarchical structures and significantly enhances the generalizability of adversarial texts. Experimental results demonstrate the effectiveness of GPI-Attack in image text retrieval tasks on multimodal datasets such as Flickr30K and MSCOCO. Additionally, the proposed gradient pruning technique is plug-and-play, showing performance improvements even when applied to baseline methods, indicating its potential as a valuable enhancement for attack performance.
- 29 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 5663-5677
Modality-Specific Interactive Attack for Vision-Language Pre-Training Models
Recent advances have heightened the interest in the adversarial transferability of Vision-Language Pre-training (VLP) models. However, most existing strategies constrained by two persistent limitations: suboptimal utilization of cross-modal interactive information, and inherent discrepancies across hierarchical textual representation. To address these challenges, we propose the Modality-Specific Interactive Attack (MSI-Attack), a novel approach that integrates semantic-level image perturbations with embedding-level text perturbations, all while maintaining minimal inter-modal constraints. In our image attack methodology, we introduce Multi-modal Integrated Gradients (MIG) to guide perturbations toward the core semantics of images, enriched by their associated deeply text information. This technique enhances transferability by capturing consistent features across various models, thereby effectively misleading similar-model perception areas. Additionally, we employ a momentum iteration strategy in conjunction with MIG, which amalgamates current and historical gradients to expedite the perturbation updates. For text attacks, we streamline the perturbation process by operating exclusively at the embedding level. This reduces semantic gaps across hierarchical structures and significantly enhances the generalizability of adversarial text. Moreover, we delve deeper into how semantic perturbations with varying degrees of similarity affect the overall attack effectiveness. Our experimental results on image-text retrieval tasks using the multi-modal datasets Flickr30K and MSCOCO underscore the efficacy of MSI-Attack. Our method achieves superior performance, setting a new state-of-the-art benchmark, all without the need for additional mechanisms.
- 29 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Information Forensics and Security
- Vol. 20 (15566013) , 5663-5677
Modality-Specific Interactive Attack for Vision-Language Pre-Training Models
Recent advances have heightened the interest in the adversarial transferability of Vision-Language Pre-training (VLP) models. However, most existing strategies constrained by two persistent limitations: suboptimal utilization of cross-modal interactive information, and inherent discrepancies across hierarchical textual representation. To address these challenges, we propose the Modality-Specific Interactive Attack (MSI-Attack), a novel approach that integrates semantic-level image perturbations with embedding-level text perturbations, all while maintaining minimal inter-modal constraints. In our image attack methodology, we introduce Multi-modal Integrated Gradients (MIG) to guide perturbations toward the core semantics of images, enriched by their associated deeply text information. This technique enhances transferability by capturing consistent features across various models, thereby effectively misleading similar-model perception areas. Additionally, we employ a momentum iteration strategy in conjunction with MIG, which amalgamates current and historical gradients to expedite the perturbation updates. For text attacks, we streamline the perturbation process by operating exclusively at the embedding level. This reduces semantic gaps across hierarchical structures and significantly enhances the generalizability of adversarial text. Moreover, we delve deeper into how semantic perturbations with varying degrees of similarity affect the overall attack effectiveness. Our experimental results on image-text retrieval tasks using the multi-modal datasets Flickr30K and MSCOCO underscore the efficacy of MSI-Attack. Our method achieves superior performance, setting a new state-of-the-art benchmark, all without the need for additional mechanisms.
- 1 January 2021
- Published by Springer Nature in Neural Processing Letters
- Vol. 54 (4) , 2645-2656
Semi-Supervised Classification of Graph Convolutional Networks with Laplacian Rank Constraints
- 1 January 2021
- Published by Springer Nature in Neural Processing Letters
- Vol. 54 (4) , 2645-2656
Semi-Supervised Classification of Graph Convolutional Networks with Laplacian Rank Constraints
- Open Access
- 1 January 2017
- Published by Atlantis Press SARL
Research and Realization of An Improved Auto-Correlation Method for Frequency Measuring
- 1 January 2017
- Published by Atlantis Press SARL
Open AccessResearch and Realization of An Improved Auto-Correlation Method for Frequency Measuring