Yaxin Xiao

20 papers A* 6Journal 13Unranked 1
YearRankTypeTitle / Venue / Authors
2026 A* conf
Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks.
AAAI
Yaxin Xiao, Qingqing Ye, Zi Liang, Haoyang Li, Ronghua Li, Huadi Zheng, Haibo Hu
2026 J jnl
FIT: Defying Catastrophic Forgetting in Continual LLM Unlearning.
CoRR
Xiaoyu Xu, Minxin Du, Kun Fang, Zi Liang, Yaxin Xiao, Zhicong Huang, Cheng Hong, Qingqing Ye, Haibo Hu
2026 J jnl
Machine Unlearning in Low-Dimensional Feature Subspace.
CoRR
Kun Fang, Qinghua Tao, Junxu Liu, Yaxin Xiao, Qingqing Ye, Jian Sun, Haibo Hu
2026 J jnl
Time-varying thresholds with Gaussian smoothing for one-bit DOA estimation in unequal power signals.
Signal Process.
Anqi Yan, Yan Zhou, Yaxin Xiao, Siyu Yang, Chuangrui Meng
2025 — conf
"Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation.
ACL (1)
Zi Liang, Qingqing Ye, Yanyun Wang, Sen Zhang, Yaxin Xiao, Ronghua Li, Jianliang Xu, Haibo Hu
2025 A* conf
A Sample-Level Evaluation and Generative Framework for Model Inversion Attacks.
AAAI
Haoyang Li, Li Bai, Qingqing Ye, Haibo Hu, Yaxin Xiao, Huadi Zheng, Jianliang Xu
2025 J jnl
A Sample-Level Evaluation and Generative Framework for Model Inversion Attacks.
CoRR
Haoyang Li, Li Bai, Qingqing Ye, Haibo Hu, Yaxin Xiao, Huadi Zheng, Jianliang Xu
2025 J jnl
Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks.
CoRR
Yaxin Xiao, Qingqing Ye, Zi Liang, Haoyang Li, Ronghua Li, Huadi Zheng, Haibo Hu
2025 A* conf
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
ICML
Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Ronghua Li
2025 J jnl
Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
CoRR
Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Ronghua Li
2025 A* conf
Dual Utilization of Perturbation for Stream Data Publication Under Local Differential Privacy.
ICDE
Rong Du, Qingqing Ye, Yaxin Xiao, Liantong Yu, Yue Fu, Haibo Hu
2025 J jnl
Dual Utilization of Perturbation for Stream Data Publication under Local Differential Privacy.
CoRR
Rong Du, Qingqing Ye, Yaxin Xiao, Liantong Yu, Yue Fu, Haibo Hu
2025 J jnl
Enhancing RODNet detection in complex road environments based on ESM and ISM methods.
Digit. Signal Process.
Yu Guo, Yaxin Xiao, Yan Zhou, Yanyan Li, Siyu Yang, Chuangrui Meng
2025 A* conf
Exploring Intrinsic Alignments Within Text Corpus.
AAAI
Zi Liang, Pinghui Wang, Ruofei Zhang, Haibo Hu, Shuo Zhang, Qingqing Ye, Nuo Xu, Yaxin Xiao, Chen Zhang, Lizhen Cui
2025 J jnl
Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy.
CoRR
Yaxin Xiao, Qingqing Ye, Li Hu, Huadi Zheng, Haibo Hu, Zi Liang, Haoyang Li, Yijie Jiao
2025 J jnl
Unlocking High-Fidelity Learning: Towards Neuron-Grained Model Extraction.
IEEE Trans. Dependable Secur. Comput.
Yaxin Xiao, Haibo Hu, Qingqing Ye, Li Tang, Zi Liang, Huadi Zheng
2024 J jnl
Alignment-Aware Model Extraction Attacks on Large Language Models.
CoRR
Zi Liang, Qingqing Ye, Yanyun Wang, Sen Zhang, Yaxin Xiao, Ronghua Li, Jianliang Xu, Haibo Hu
2024 J jnl
DeepMark: A Scalable and Robust Framework for DeepFake Video Detection.
ACM Trans. Priv. Secur.
Li Tang, Qingqing Ye, Haibo Hu, Qiao Xue, Yaxin Xiao, Jin Li
2024 J jnl
Why Are My Prompts Leaked? Unraveling Prompt Extraction Threats in Customized Large Language Models.
CoRR
Zi Liang, Haibo Hu, Qingqing Ye, Yaxin Xiao, Haoyang Li
2022 A* conf
MExMI: Pool-based Active Model Extraction Crossover Membership Inference.
NeurIPS
Yaxin Xiao, Qingqing Ye, Haibo Hu, Huadi Zheng, Chengfang Fang, Jie Shi