Kanghua Mo

18 papers A* 1Journal 15Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
HPA: Manipulating deep reinforcement learning via adversarial interaction.
J. Syst. Archit.
Kanghua Mo, Zhengxin Zhang, Yuanzhi Zhang, Yucheng Long, Zhengdao Li
2026 J jnl
TransLock: Securing LLM deployment for software applications via self-locking watermarks.
Empir. Softw. Eng.
Pei-Gen Ye, Zhenxin Zhang, Kanghua Mo, Yun Peng
2026 J jnl
Your Non-Transferable Learning is Fragile: Practical Breach of Protected Models.
IEEE Trans. Inf. Forensics Secur.
Anli Yan, Huali Ren, Kanghua Mo, Pei-Gen Ye, Zhenxin Zhang, Hongyang Yan, Jin Li
2025 J jnl
Attractive Metadata Attack: Inducing LLM Agents to Invoke Malicious Tools.
CoRR
Kanghua Mo, Li Hu, Yucheng Long, Zhihao Li
2025 A* conf
Distraction is All You Need for Multimodal Large Language Model Jailbreaking.
CVPR
Zuopeng Yang, Jiluan Fan, Anli Yan, Erdun Gao, Xin Lin, Tao Li, Kanghua Mo, Changyu Dong
2025 J jnl
Distraction is All You Need for Multimodal Large Language Model Jailbreaking.
CoRR
Zuopeng Yang, Jiluan Fan, Anli Yan, Erdun Gao, Xin Lin, Tao Li, Kanghua Mo, Changyu Dong
2025 J jnl
Enhancing Model Intellectual Property Protection With Robustness Fingerprint Technology.
IEEE Trans. Inf. Forensics Secur.
Anli Yan, Huali Ren, Kanghua Mo, Zhenxin Zhang, Shaowei Wang, Jin Li
2025 J jnl
Inverse correction-optimized vertical federated unlearning.
J. Supercomput.
Lang Li, Li Hu, Kanghua Mo, Ziyu Ding, Yaqi Wu, Hongyang Yan, Jin Li
2024 J jnl
Exploring the vulnerability of self-supervised monocular depth estimation models.
Inf. Sci.
Ruitao Hou, Kanghua Mo, Yucheng Long, Ning Li, Yuan Rao
2024 J jnl
Security and Privacy Issues in Deep Reinforcement Learning: Threats and Countermeasures.
ACM Comput. Surv.
Kanghua Mo, Peigen Ye, Xiaojun Ren, Shaowei Wang, Wenjun Li, Jin Li
2023 J jnl
Attacking Deep Reinforcement Learning With Decoupled Adversarial Policy.
IEEE Trans. Dependable Secur. Comput.
Kanghua Mo, Weixuan Tang, Jin Li, Xu Yuan
2023 — conf
Decision Poisson: From Universal Gravitation to Offline Reinforcement Learning.
AIS&P (1)
Heqiu Cai, Zhanao Zhang, Zhicong Yao, Kanghua Mo, Dixuan Chen, Hongyang Yan
2023 J jnl
Empirical study of privacy inference attack against deep reinforcement learning models.
Connect. Sci.
Huaicheng Zhou, Kanghua Mo, Teng Huang, Yongjin Li
2022 J jnl
An efficient adversarial example generation algorithm based on an accelerated gradient iterative fast gradient.
Comput. Stand. Interfaces
Jiabao Liu, Qixiang Zhang, Kanghua Mo, Xiaoyu Xiang, Jin Li, Debin Cheng, Rui Gao, Beishui Liu, Kongyang Chen, Guanjie Wei
2022 J jnl
ESM: Selfish mining under ecological footprint.
Inf. Sci.
Shan Ai, Guoyu Yang, Chang Chen, Kanghua Mo, Wangyong Lv, Arthur Sandor Voundi Koe
2022 J jnl
Sender anonymity: Applying ring signature in gateway-based blockchain for IoT is not enough.
Inf. Sci.
Arthur Sandor Voundi Koe, Shan Ai, Pengfei Huang, Anli Yan, Juan Tang, Qi Chen, Kanghua Mo, Wanqing Jie, Shiwen Zhang
2021 J jnl
Querying little is enough: Model inversion attack via latent information.
Int. J. Intell. Syst.
Kanghua Mo, Xiaozhang Liu, Teng Huang, Anli Yan
2020 — conf
Querying Little Is Enough: Model Inversion Attack via Latent Information.
ML4CS (2)
Kanghua Mo, Teng Huang, Xiaoyu Xiang