Publications

2025

[4] Wang, L., Ying, Z., Zhang, T., Liang, S., Hu, S., Zhang, M., … & Liu, X. (2025). Manipulating Multimodal Agents via Cross-Modal Prompt Injection. arXiv preprint arXiv:2504.14348.Link

[3] Zonghao Ying. et al. Towards Understanding the Safety Boundaries of DeepSeek Models: Evaluation and Findings.Link

[2] Zonghao Ying. et al. Reasoning-Augmented Conversation for Multi-Turn Jailbreak Attacks on Large Language Models.Link

[1] Jing, Z., Ying, Z., Wang, L., Liang, S., Liu, A., Liu, X., & Tao, D. (2025). CogMorph: Cognitive Morphing Attacks for Text-to-Image Models. arXiv preprint arXiv:2501.11815.Link

2024

[1] Zonhao Ying. Chinese Edition of “AI for Cybersecurity: A Handbook of Use Cases”

[2] Zonhao Ying. Head First Cryptography

[3] Zonghao Ying. Advances in Foundation Model Security

[4] Zonghao Ying. et al. Jailbreak Vision Language Models via Bi-Modal Adversarial Prompt.Link

[5] Zonghao Ying. et al. Unveiling the Safety of GPT-4o: An Empirical Study using Jailbreak Attacks. Link(Chinese)

[6] Zonghao Ying. et al. SafeBench: A Safety Evaluation Framework for Multimodal Large Language Models. Project page, Link.)

2023

[1] YING Zonghao, WU Bin. Backdoor Attack on Deep Learning Models:A Survey[J]. Computer Science, 2023, 50(3): 333-350.

[2] Ying, Z., Wu, B. DLP: towards active defense against backdoor attacks with decoupled learning process. Cybersecurity 6, 9 (2023).

[3] Ying, Z., Wu, B. NBA: defensive distillation for backdoor removal via neural behavior alignment. Cybersecurity 6, 20 (2023).

2022

[1] Encrypted Malicious Traffic Detection: A Survey (accepted by “Information Security & Communication Privacy”, in Chinese). Zonghao Ying, Bin Wu. 2022

2021

[1] DeeSCVHunter: A Deep Learning-Based Framework for Smart Contract Vulnerability Detection. Xingxin Yu, Haoyue Zhao, Botao Hou, Zonghao Ying, Bin Wu. IJCNN, 2021