Yinghan Zhou

16 papers A* 1A 1Journal 13Unranked 1
YearRankTypeTitle / Venue / Authors
2026 A* conf
BeDKD: Backdoor Defense Based on Directional Mapping Module and Adversarial Knowledge Distillation.
AAAI
Zhengxian Wu, Juan Wen, Wanli Peng, Yinghan Zhou, Changtong Dou, Yiming Xue
2026 J jnl
Inhibitory Attacks on Backdoor-based Fingerprinting for Large Language Models.
CoRR
Hang Fu, Wanli Peng, Yinghan Zhou, Jiaxuan Wu, Juan Wen, Yiming Xue
2025 J jnl
BadApex: Backdoor Attack Based on Adaptive Optimization Mechanism of Black-box Large Language Models.
CoRR
Zhengxian Wu, Juan Wen, Wanli Peng, Ziwei Zhang, Yinghan Zhou, Yiming Xue
2025 J jnl
BeDKD: Backdoor Defense based on Dynamic Knowledge Distillation and Directional Mapping Modulator.
CoRR
Zhengxian Wu, Juan Wen, Wanli Peng, Yinghan Zhou, Changtong Dou, Yiming Xue
2025 J jnl
Cognitive Surgery: The Awakening of Implicit Territorial Awareness in LLMs.
CoRR
Yinghan Zhou, Weifeng Zhu, Juan Wen, Wanli Peng, Zhengxian Wu, Yiming Xue
2025 J jnl
EditMF: Drawing an Invisible Fingerprint for Your Large Language Models.
CoRR
Jiaxuan Wu, Yinghan Zhou, Wanli Peng, Yiming Xue, Juan Wen, Ping Zhong
2025 J jnl
GTSD: Generative Text Steganography Based on Diffusion Model.
CoRR
Zhengxian Wu, Juan Wen, Yiming Xue, Ziwei Zhang, Yinghan Zhou
2025 J jnl
IBSD: Iterable Black-Box Self-Defense Against Backdoor Attacks.
IEEE Signal Process. Lett.
Zhengxian Wu, Juan Wen, Wanli Peng, Yinghan Zhou, Ziwei Zhang
2025 — conf
Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations.
NAACL (Long Papers)
Yinghan Zhou, Juan Wen, Wanli Peng, Yiming Xue, Ziwei Zhang, Zhengxian Wu
2025 J jnl
Kill two birds with one stone: generalized and robust AI-generated text detection via dynamic perturbations.
CoRR
Yinghan Zhou, Juan Wen, Wanli Peng, Yiming Xue, Ziwei Zhang, Zhengxian Wu
2025 J jnl
MiZero: The Shadowy Defender Against Text Style Infringements.
CoRR
Ziwei Zhang, Juan Wen, Wanli Peng, Zhengxian Wu, Yinghan Zhou, Yiming Xue
2025 J jnl
SLIP: Soft Label Mechanism and Key-Extraction-Guided CoT-based Defense Against Instruction Backdoor in APIs.
CoRR
Zhengxian Wu, Juan Wen, Wanli Peng, Haowei Chang, Yinghan Zhou, Yiming Xue
2025 J jnl
Self-Disguise Attack: Induce the LLM to disguise itself for AIGT detection evasion.
CoRR
Yinghan Zhou, Juan Wen, Wanli Peng, Zhengxian Wu, Ziwei Zhang, Yiming Xue
2024 J jnl
C-Net: A Compression-Based Lightweight Network for Machine-Generated Text Detection.
IEEE Signal Process. Lett.
Yinghan Zhou, Juan Wen, Jianghao Jia, Liting Gao, Ziwei Zhang
2024 A conf
Domain Adaptational Steganographic Text Detection Using Few-Shot Adversary-Refinement Framework.
ECAI
Ziwei Zhang, Juan Wen, Yinghan Zhou, Liting Gao, Yiming Xue
2024 J jnl
Linguistic Steganalysis via Probabilistic Weighted Contrastive Learning.
IEEE Signal Process. Lett.
Liting Gao, Juan Wen, Ziwei Zhang, Guangying Fan, Yinghan Zhou