Zheli Liu

5 papers · 2024–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (13)

Venues

ACL (3) EMNLP (1) ICLR (1)

Top co-authors

Biao Yi (5) Tong Li (4) Baolei Zhang (3) Sishuo Chen (2) Lihai Nie (2) Tiansheng Huang (2) Yiming Li (2) Zhixuan Chu (1) Li Shen (1) Peiqi Yu (1)

Research topics

Artificial Intelligence (5) Core AI (5) Deep Learning (2) Machine Learning (2) Learning Types (2) Computer Science (1) Natural Language Processing (1) Application Areas (1) Applications · Natural Language Processing (1) Applications · Computer Science (1) Models (1) Techniques (1)

Keywords

backdoor attack (2) large language model (2) supervised learning (1) ai safety (1) safety alignment (1) adversarial defense (1) model collapse (1) copyright protection (1) watermark detection (1) fine-tuning attack (1) hallucination detection (1) harmful fine-tuning (1) cross-domain generalization (1) black-box defense (1) internal state (1) embedding watermarking (1) copyright infringement (1) selective unlearning (1) activation space (1) backdoor watermarking (1)

Papers

CTRAP: Embedding Collapse Trap to Safeguard Large Language Models from Harmful Fine-Tuning ACL 2026 Probe before You Talk: Towards Black-box Defense against Backdoor Unalignment for Large Language Models ICLR 2025 Prompt-Guided Internal States for Hallucination Detection of Large Language Models ACL 2025 Your Semantic-Independent Watermark is Fragile: A Semantic Perturbation Attack against EaaS Watermark EMNLP 2025 BadActs: A Universal Backdoor Defense in the Activation Space ACL 2024