Kanghua Mo - Publications, H-index & Citations

Kanghua Mo

School of Artificial Intelligence

6H指数

15论文数

191被引数

收录论文 7

发表时间

TransLock: Securing LLM deployment for software applications via self-locking watermarks TransLock：通过自锁定水印为软件应用程序的LLM部署提供安全保障

Empirical Software Engineering

IF3.6

2025-12-05

PREAI

Pei-Gen Ye; Zhenxin Zhang; Kanghua Mo; Yun Peng

Enhancing Model Intellectual Property Protection With Robustness Fingerprint Technology 利用鲁棒性指纹技术增强模型知识产权保护

IEEE Transactions on Information Forensics and Security

IF8

2025-01-01

PREAI

Anli Yan; Huali Ren; Kanghua Mo; Zhenxin Zhang; Shaowei Wang; Jin Li

Security and Privacy Issues in Deep Reinforcement Learning: Threats and Countermeasures 深度强化学习中的安全与隐私问题: 威胁与对策

ACM COMPUTING SURVEYS

IF28

2024-02-23

PREAI

Mo, Kanghua; Ye, Peigen; Ren, Xiaojun; Wang, Shaowei; Li, Wenjun; Li, Jin

Empirical study of privacy inference attack against deep reinforcement learning models

CONNECTION SCIENCE

IF3.4

2023-07-11

OAAI

Zhou, Huaicheng; Mo, Kanghua; Huang, Teng; Li, Yongjin

Attacking Deep Reinforcement Learning With Decoupled Adversarial Policy 使用解耦对抗策略攻击深度强化学习

IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING

IF7.5

2023-01-01

PREAI

Mo, Kanghua; Tang, Weixuan; Li, Jin; Yuan, Xu

An efficient adversarial example generation algorithm based on an accelerated gradient iterative fast gradient

COMPUTER STANDARDS & INTERFACES

IF3.1

2022-08-01

PREAI

Liu, Jiabao; Zhang, Qixiang; Mo, Kanghua; Xiang, Xiaoyu; Li, Jin; Cheng, Debin; Gao, Rui; Liu, Beishui; Chen, Kongyang; Wei, Guanjie

Querying little is enough: Model inversion attack via latent information

INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS

IF3.7

2020-10-29

PREAI

Mo, Kanghua; Liu, Xiaozhang; Huang, Teng; Yan, Anli

研究方向