Kanghua Mo

PhD student, School of Artificial Intelligence, Guangzhou University

Joined

June 2022

Names

Kanghua Mo (Preferred)

Emails

****@gmail.com (Confirmed)

Personal Links

Google Scholar

DBLP

Career & Education History

PhD student

School of Artificial Intelligence, Guangzhou University (gzhu.edu.cn)

2022 – 2026

Advisors, Relations & Conflicts

PhD Advisor

Jin Li

2019 – 2026

Expertise

LLM security

2024 – Present

deep reinforcement learning

2019 – 2024

Publications

Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools
Kanghua Mo, Li Hu, Yucheng Long, Zhihao li
- NeurIPS 2025 poster
- Readers: Everyone
Distraction is All You Need for Multimodal Large Language Model Jailbreaking
Zuopeng Yang, Jiluan Fan, Anli Yan, Erdun Gao, Xin Lin, Tao Li, Kanghua Mo, Changyu Dong
- CoRR 2025
- Readers: Everyone
Security and Privacy Issues in Deep Reinforcement Learning: Threats and Countermeasures
Kanghua Mo, Peigen Ye, Xiaojun Ren, Shaowei Wang, Wenjun Li, Jin Li
- ACM Comput. Surv. 2024
- Readers: Everyone
Exploring the vulnerability of self-supervised monocular depth estimation models
Ruitao Hou, Kanghua Mo, Yucheng Long, Ning Li, Yuan Rao
- Inf. Sci. 2024
- Readers: Everyone
Empirical study of privacy inference attack against deep reinforcement learning models
Huaicheng Zhou, Kanghua Mo, Teng Huang, Yongjin Li
- Connect. Sci. 2023
- Readers: Everyone
Attacking Deep Reinforcement Learning With Decoupled Adversarial Policy
Kanghua Mo, Weixuan Tang, Jin Li, Xu Yuan
- Published: 01 Jan 2023, Last Modified: 12 May 2023
- IEEE Trans. Dependable Secur. Comput. 2023
- Readers: Everyone
An efficient adversarial example generation algorithm based on an accelerated gradient iterative fast gradient
Jiabao Liu, Qixiang Zhang, Kanghua Mo, Xiaoyu Xiang, Jin Li, Debin Cheng, Rui Gao, Beishui Liu, Kongyang Chen, Guanjie Wei
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- Comput. Stand. Interfaces 2022
- Readers: Everyone
Sender anonymity: Applying ring signature in gateway-based blockchain for IoT is not enough
Arthur Sandor Voundi Koe, Shan Ai, Pengfei Huang, Anli Yan, Juan Tang, Qi Chen, Kanghua Mo, Wanqing Jie, Shiwen Zhang
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- Inf. Sci. 2022
- Readers: Everyone
ESM: Selfish mining under ecological footprint
Shan Ai, Guoyu Yang, Chang Chen, Kanghua Mo, Wangyong Lv, Arthur Sandor Voundi Koe
- Published: 01 Jan 2022, Last Modified: 12 May 2023
- Inf. Sci. 2022
- Readers: Everyone
Querying little is enough: Model inversion attack via latent information
Kanghua Mo, Xiaozhang Liu, Teng Huang, Anli Yan
- Published: 01 Jan 2021, Last Modified: 12 May 2023
- Int. J. Intell. Syst. 2021
- Readers: Everyone

View all 11 publications

Co-Authors

View all 42 co-authors