Zi Liang

Venues

Frequent coauthors

Papers

1. Beyond Prompt Engineering: A Systematic Analysis of Prompt Lexical Sensitivity and Its Impacts on Quality
   ACL 2026 ·

   Qipeng Xie

   DBLP profile ↗ORCID search ↗
2. Class-feature Watermark: A Resilient Black-box Watermark Against Model Extraction Attacks
   AAAI 2026 ·

   Yaxin Xiao

   DBLP profile ↗ORCID search ↗
3. Decoding Web Memorization: A Semantic Membership Inference Attack on LLMs
   WWW 2026 ·

   Zhiyao Wu

   DBLP profile ↗ORCID search ↗
4. From Domains to Instances: Dual-Granularity Data Synthesis for LLM Unlearning
   ACL 2026 ·

   Xiaoyu Xu

   DBLP profile ↗ORCID search ↗
5. How Much Do Large Language Model Cheat on Evaluation? Benchmarking Overestimation Under the One-Time-Pad-Based Framework
   AAAI 2026 · Zi Liang
6. "Yes, My LoRD." Guiding Language Model Extraction with Locality Reinforced Distillation
   ACL 2025 · Zi Liang
7. Cross-Modal 3D Representation with Multi-View Images and Point Clouds
   CVPR 2025 ·

   Ziyang Zhou

   DBLP profile ↗ORCID search ↗
8. Does Low Rank Adaptation Lead to Lower Robustness against Training-Time Attacks?
   ICML 2025 · Zi Liang
9. Exploring Intrinsic Alignments Within Text Corpus
   AAAI 2025 · Zi Liang
10. Reminiscence Attack on Residuals: Exploiting Approximate Machine Unlearning for Privacy
    ICCV 2025 ·

    Yaxin Xiao

    DBLP profile ↗ORCID search ↗
11. Toward Efficient Inference Attacks: Shadow Model Sharing via Mixture-of-Experts
    NeurIPS 2025 ·

    Li Bai

    DBLP profile ↗ORCID search ↗
12. Virus Infection Attack on LLMs: Your Poisoning Can Spread "VIA" Synthetic Data
    NeurIPS 2025 · Zi Liang
13. MERGE: Fast Private Text Generation
    AAAI 2024 · Zi Liang
14. PAIR: Pre-denosing Augmented Image Retrieval Model for Defending Adversarial Patches
    ACM MM 2024 ·

    Ziyang Zhou

    DBLP profile ↗ORCID search ↗
15. TSFool: Crafting Highly-Imperceptible Adversarial Time Series Through Multi-Objective Attack
    ECAI 2024 ·

    Yanyun Wang

    DBLP profile ↗ORCID search ↗